Resync the lexers with Scintillua

- Resync the lexers with Scintillua

- Update the lexer readme

- Update `zenburn` theme to fix some highlighting issues

- lexers: redirect print function to vis:info()

- Fix support for custom style names

- As per error message "lexer.delimited_range() is deprecated, use lexer.range()".

- Remove remaining `lexer.delimited_range()` call

- Set syntax to `nil` if the file type has no matching lexer

- Updated Go lexer for Go 1.18.

- lexers/dsv: convert to new lexer format

  (cherry picked from commit 9edbc3cd9ea1d7142b1305840432a3d2739e755a)

- lexers/gemini: disable legacy gemini lexer

  This reverts commit 468f9ee1b027a7ce98b1a249fa1af5888feeb989.

  It is in legacy format and of questionable quality. Ideally it
  should be contributed upstream from where it will eventually
  trickle down to us.

- lexers/git-rebase: convert to new lexer format

  (cherry picked from commit 4000a4cc9ac4a4c2869dfae772b977a82aee8d8c)

- lexers/strace: convert to new lexer format

  (cherry picked from commit e420451320d97eb164f5629c1bcfab0b595be29d)

- lexers/typescript: add new upstream lexer revision 28e2b60

  (cherry picked from commit 7326e6deecdaa75fa94ae9ebdb653f9f907b33f2)

- use `package.searchpath` instead of a local `searchpath` function

- Restore `filetype: support filetype detection via hashbang`

- Remove redundant comment

- Restore gemini lexer

1 files changed, 88 insertions, 114 deletions

diff --git a/lua/lexers/moonscript.lua b/lua/lexers/moonscript.lua
index c0a00d2..f9bc4dd 100644
--- a/lua/lexers/moonscript.lua
+++ b/lua/lexers/moonscript.lua
@@ -1,82 +1,71 @@
--- Copyright 2016-2017 Alejandro Baez (https://keybase.io/baez). See LICENSE.
+-- Copyright 2016-2022 Alejandro Baez (https://keybase.io/baez). See LICENSE.
 -- Moonscript LPeg lexer.
 
-local l = require('lexer')
-local token, word_match = l.token, l.word_match
-local P, S, R = lpeg.P, lpeg.S, lpeg.R
+local lexer = require('lexer')
+local token, word_match = lexer.token, lexer.word_match
+local P, S = lpeg.P, lpeg.S
 
-local M = {_NAME = 'moonscript'}
+local lex = lexer.new('moonscript', {fold_by_indentation = true})
 
 -- Whitespace.
-local ws = token(l.WHITESPACE, l.space^1)
+lex:add_rule('whitspace', token(lexer.WHITESPACE, lexer.space^1))
 
-local longstring = lpeg.Cmt('[' * lpeg.C(P('=')^0) * '[',
-                            function(input, index, eq)
-                              local _, e = input:find(']'..eq..']', index, true)
-                              return (e or #input) + 1
-                            end)
-
--- Comments.
-local line_comment = '--' * l.nonnewline^0
-local block_comment = '--' * longstring
-local comment = token(l.COMMENT, block_comment + line_comment)
-
--- Strings.
-local sq_str = l.delimited_range("'", false, true)
-local dq_str = l.delimited_range('"', false, true)
-
-local string = token(l.STRING, sq_str + dq_str) +
-               token('longstring', longstring)
-
--- Numbers.
-local number = token(l.NUMBER, l.float + l.integer)
+-- Table keys.
+lex:add_rule('tbl_key', token('tbl_key', lexer.word * ':' + ':' * lexer.word))
+lex:add_style('tbl_key', lexer.STYLE_REGEX)
 
 -- Keywords.
-local keyword = token(l.KEYWORD, word_match {
+lex:add_rule('keyword', token(lexer.KEYWORD, word_match{
   -- Lua.
-  'and', 'break', 'do', 'else', 'elseif', 'false', 'for', 'if', 'in', 'local',
-  'nil', 'not', 'or', 'return', 'then', 'true', 'while',
+  'and', 'break', 'do', 'else', 'elseif', 'false', 'for', 'if', 'in', 'local', 'nil', 'not', 'or',
+  'return', 'then', 'true', 'while',
   -- Moonscript.
-  'continue', 'class', 'export', 'extends', 'from', 'import', 'super', 'switch',
-  'unless', 'using', 'when', 'with'
-})
+  'continue', 'class', 'export', 'extends', 'from', 'import', 'super', 'switch', 'unless', 'using',
+  'when', 'with'
+}))
 
--- Constants.
-local constant = token(l.CONSTANT, word_match{
-  '_G', '_VERSION',
-  -- Added in 5.2.
-  '_ENV'
-})
+-- Error words.
+lex:add_rule('error', token(lexer.ERROR, word_match('function end')))
+
+-- Self reference.
+lex:add_rule('self_ref', token('self_ref', '@' * lexer.word^-1 + 'self'))
+lex:add_style('self_ref', lexer.styles.label)
 
 -- Functions.
-local func = token(l.FUNCTION, word_match{
-  'assert', 'collectgarbage', 'dofile', 'error', 'getmetatable', 'ipairs',
-  'load', 'loadfile', 'next', 'pairs', 'pcall', 'print', 'rawequal', 'rawget',
-  'rawset', 'require', 'select', 'setmetatable', 'tonumber', 'tostring', 'type',
-  'xpcall',
+lex:add_rule('function', token(lexer.FUNCTION, word_match{
+  'assert', 'collectgarbage', 'dofile', 'error', 'getmetatable', 'ipairs', 'load', 'loadfile',
+  'next', 'pairs', 'pcall', 'print', 'rawequal', 'rawget', 'rawset', 'require', 'select',
+  'setmetatable', 'tonumber', 'tostring', 'type', 'xpcall',
   -- Added in 5.2.
   'rawlen'
-})
+}))
+
+-- Constants.
+lex:add_rule('constant', token(lexer.CONSTANT, word_match{
+  '_G', '_VERSION',
+  -- Added in 5.2.
+  '_ENV'
+}))
 
 -- Libraries.
-local library = token('library', word_match({
+lex:add_rule('library', token('library', word_match{
   -- Coroutine.
-  'coroutine', 'coroutine.create', 'coroutine.resume', 'coroutine.running',
-  'coroutine.status', 'coroutine.wrap', 'coroutine.yield',
+  'coroutine', 'coroutine.create', 'coroutine.resume', 'coroutine.running', 'coroutine.status',
+  'coroutine.wrap', 'coroutine.yield',
   -- Coroutine added in 5.3.
   'coroutine.isyieldable',
   -- Module.
-  'package', 'package.cpath', 'package.loaded', 'package.loadlib',
-  'package.path', 'package.preload',
+  'package', 'package.cpath', 'package.loaded', 'package.loadlib', 'package.path',
+  'package.preload',
   -- Module added in 5.2.
   'package.config', 'package.searchers', 'package.searchpath',
   -- UTF-8 added in 5.3.
-  'utf8', 'utf8.char', 'utf8.charpattern', 'utf8.codepoint', 'utf8.codes',
-  'utf8.len', 'utf8.offset',
+  'utf8', 'utf8.char', 'utf8.charpattern', 'utf8.codepoint', 'utf8.codes', 'utf8.len',
+  'utf8.offset',
   -- String.
-  'string', 'string.byte', 'string.char', 'string.dump', 'string.find',
-  'string.format', 'string.gmatch', 'string.gsub', 'string.len', 'string.lower',
-  'string.match', 'string.rep', 'string.reverse', 'string.sub', 'string.upper',
+  'string', 'string.byte', 'string.char', 'string.dump', 'string.find', 'string.format',
+  'string.gmatch', 'string.gsub', 'string.len', 'string.lower', 'string.match', 'string.rep',
+  'string.reverse', 'string.sub', 'string.upper',
   -- String added in 5.3.
   'string.pack', 'string.packsize', 'string.unpack',
   -- Table.
@@ -86,29 +75,24 @@ local library = token('library', word_match({
   -- Table added in 5.3.
   'table.move',
   -- Math.
-  'math', 'math.abs', 'math.acos', 'math.asin', 'math.atan', 'math.ceil',
-  'math.cos', 'math.deg', 'math.exp', 'math.floor', 'math.fmod', 'math.huge',
-  'math.log', 'math.max', 'math.min', 'math.modf', 'math.pi', 'math.rad',
-  'math.random', 'math.randomseed', 'math.sin', 'math.sqrt', 'math.tan',
+  'math', 'math.abs', 'math.acos', 'math.asin', 'math.atan', 'math.ceil', 'math.cos', 'math.deg',
+  'math.exp', 'math.floor', 'math.fmod', 'math.huge', 'math.log', 'math.max', 'math.min',
+  'math.modf', 'math.pi', 'math.rad', 'math.random', 'math.randomseed', 'math.sin', 'math.sqrt',
+  'math.tan',
   -- Math added in 5.3.
-  'math.maxinteger', 'math.mininteger', 'math.tointeger', 'math.type',
-  'math.ult',
+  'math.maxinteger', 'math.mininteger', 'math.tointeger', 'math.type', 'math.ult',
   -- IO.
-  'io', 'io.close', 'io.flush', 'io.input', 'io.lines', 'io.open', 'io.output',
-  'io.popen', 'io.read', 'io.stderr', 'io.stdin', 'io.stdout', 'io.tmpfile',
-  'io.type', 'io.write',
+  'io', 'io.close', 'io.flush', 'io.input', 'io.lines', 'io.open', 'io.output', 'io.popen',
+  'io.read', 'io.stderr', 'io.stdin', 'io.stdout', 'io.tmpfile', 'io.type', 'io.write',
   -- OS.
-  'os', 'os.clock', 'os.date', 'os.difftime', 'os.execute', 'os.exit',
-  'os.getenv', 'os.remove', 'os.rename', 'os.setlocale', 'os.time',
-  'os.tmpname',
+  'os', 'os.clock', 'os.date', 'os.difftime', 'os.execute', 'os.exit', 'os.getenv', 'os.remove',
+  'os.rename', 'os.setlocale', 'os.time', 'os.tmpname',
   -- Debug.
-  'debug', 'debug.debug', 'debug.gethook', 'debug.getinfo', 'debug.getlocal',
-  'debug.getmetatable', 'debug.getregistry', 'debug.getupvalue',
-  'debug.sethook', 'debug.setlocal', 'debug.setmetatable', 'debug.setupvalue',
-  'debug.traceback',
+  'debug', 'debug.debug', 'debug.gethook', 'debug.getinfo', 'debug.getlocal', 'debug.getmetatable',
+  'debug.getregistry', 'debug.getupvalue', 'debug.sethook', 'debug.setlocal', 'debug.setmetatable',
+  'debug.setupvalue', 'debug.traceback',
   -- Debug added in 5.2.
-  'debug.getuservalue', 'debug.setuservalue', 'debug.upvalueid',
-  'debug.upvaluejoin',
+  'debug.getuservalue', 'debug.setuservalue', 'debug.upvalueid', 'debug.upvaluejoin',
 
   --- MoonScript 0.3.1 standard library.
   -- Printing functions.
@@ -120,51 +104,41 @@ local library = token('library', word_match({
   -- Misc functions.
   'fold',
   -- Debug functions.
-  'debug.upvalue',
-}, '.'))
+  'debug.upvalue'
+}))
+lex:add_style('library', lexer.styles.type)
 
 -- Identifiers.
-local identifier = token(l.IDENTIFIER, l.word)
-local proper_ident = token('proper_ident', R('AZ') * l.word)
-local tbl_key = token('tbl_key', l.word * ':' + ':' * l.word )
+local identifier = token(lexer.IDENTIFIER, lexer.word)
+local proper_ident = token('proper_ident', lexer.upper * lexer.word)
+lex:add_rule('identifier', proper_ident + identifier)
+lex:add_style('proper_ident', lexer.styles.class)
 
-local fndef = token('fndef', P('->') + '=>')
-local err = token(l.ERROR, word_match{'function', 'end'})
+-- Strings.
+local sq_str = lexer.range("'", false, false)
+local dq_str = lexer.range('"', false, false)
+local longstring = lpeg.Cmt('[' * lpeg.C(P('=')^0) * '[', function(input, index, eq)
+  local _, e = input:find(']' .. eq .. ']', index, true)
+  return (e or #input) + 1
+end)
+lex:add_rule('string', token(lexer.STRING, sq_str + dq_str) + token('longstring', longstring))
+lex:add_style('longstring', lexer.styles.string)
+
+-- Comments.
+local line_comment = lexer.to_eol('--')
+local block_comment = '--' * longstring
+lex:add_rule('comment', token(lexer.COMMENT, block_comment + line_comment))
+
+-- Numbers.
+lex:add_rule('number', token(lexer.NUMBER, lexer.number))
+
+-- Function definition.
+lex:add_rule('fndef', token('fndef', P('->') + '=>'))
+lex:add_style('fndef', lexer.styles.preprocessor)
 
 -- Operators.
-local symbol = token('symbol', S('(){}[]'))
-local operator = token(l.OPERATOR, S('+-*!\\/%^#=<>;:,.'))
+lex:add_rule('operator', token(lexer.OPERATOR, S('+-*!\\/%^#=<>;:,.')))
+lex:add_rule('symbol', token('symbol', S('(){}[]')))
+lex:add_style('symbol', lexer.styles.embedded)
 
--- Self reference.
-local self_var = token('self_ref', '@' * l.word + 'self')
-
-M._rules = {
-  {'whitespace', ws},
-  {'keyword', keyword},
-  {'error', err},
-  {'self', self_var},
-  {'function', func},
-  {'constant', constant},
-  {'library', library},
-  {'identifier', proper_ident + tbl_key + identifier},
-  {'string', string},
-  {'comment', comment},
-  {'number', number},
-  {'fndef', fndef},
-  {'symbol', symbol},
-  {'operator', operator},
-}
-
-M._tokenstyles = {
-  longstring = l.STYLE_STRING,
-  library = l.STYLE_TYPE,
-  self_ref = l.STYLE_LABEL,
-  proper_ident = l.STYLE_CLASS,
-  fndef = l.STYLE_PREPROCESSOR,
-  symbol = l.STYLE_EMBEDDED,
-  tbl_key = l.STYLE_REGEX,
-}
-
-M._FOLDBYINDENTATION = true
-
-return M
+return lex