aboutsummaryrefslogtreecommitdiff
path: root/lua/lexers/zig.lua
diff options
context:
space:
mode:
Diffstat (limited to 'lua/lexers/zig.lua')
-rw-r--r--lua/lexers/zig.lua167
1 files changed, 65 insertions, 102 deletions
diff --git a/lua/lexers/zig.lua b/lua/lexers/zig.lua
index f8eb74b..efc3a1f 100644
--- a/lua/lexers/zig.lua
+++ b/lua/lexers/zig.lua
@@ -1,130 +1,93 @@
--- Copyright 2020 Karchnu karchnu@karchnu.fr.
+-- Copyright 2020-2022 Karchnu karchnu@karchnu.fr. See LICENSE.
-- Zig LPeg lexer.
--- (Based on the C++ LPeg lexer from Mitchell mitchell.att.foicica.com.)
+-- (Based on the C++ LPeg lexer from Mitchell.)
-local l = require('lexer')
-local token, word_match = l.token, l.word_match
-local P, R, S = lpeg.P, lpeg.R, lpeg.S
+local lexer = require('lexer')
+local token, word_match = lexer.token, lexer.word_match
+local P, S = lpeg.P, lpeg.S
-local M = {_NAME = 'zig'}
+local lex = lexer.new('zig')
-- Whitespace.
-local ws = token(l.WHITESPACE, l.space^1)
-
--- Comments.
-local line_comment = '//' * l.nonnewline_esc^0
-local comment = token(l.COMMENT, line_comment)
--- For documentation, I took the liberty of using the preprocessor coloration,
--- since it doesn't exist in Zig anyway.
-local doc_comment = '///' * l.nonnewline_esc^0
-local preprocessor = token(l.PREPROCESSOR, doc_comment)
-
--- Strings.
-local sq_str = P('L')^-1 * l.delimited_range("'", true)
-local dq_str = P('L')^-1 * l.delimited_range('"', true)
-local string = token(l.STRING, sq_str + dq_str)
-
--- Numbers.
-local number = token(l.NUMBER, l.float + l.integer)
+lex:add_rule('whitespace', token(lexer.WHITESPACE, lexer.space^1))
-- Keywords.
-local keyword = token(l.KEYWORD, word_match{
-
+lex:add_rule('keyword', token(lexer.KEYWORD, word_match{
-- Keywords.
- 'inline', 'pub', 'fn', 'comptime', 'const',
- 'extern', 'return', 'var', 'usingnamespace',
-
+ 'inline', 'pub', 'fn', 'comptime', 'const', 'extern', 'return', 'var', 'usingnamespace',
-- Defering code blocks.
'defer', 'errdefer',
-
-- Functions and structures related keywords.
- 'align', 'allowzero',
- 'noalias', 'noinline',
- 'callconv', 'packed', 'linksection',
- 'unreachable',
- 'test',
- 'asm', 'volatile',
-
+ 'align', 'allowzero', 'noalias', 'noinline', 'callconv', 'packed', 'linksection', 'unreachable',
+ 'test', 'asm', 'volatile',
-- Parallelism and concurrency related keywords.
- 'async', 'await', 'noasync',
- 'suspend', 'nosuspend', 'resume',
- 'threadlocal','anyframe',
-
+ 'async', 'await', 'noasync', 'suspend', 'nosuspend', 'resume', 'threadlocalanyframe',
-- Control flow: conditions and loops.
- 'if', 'else', 'orelse',
- 'or', 'and',
- 'while', 'for', 'switch', 'continue', 'break',
- 'catch', 'try',
-
- -- Not keyword, but overly used variable name with always the same semantic.
- 'self',
-})
+ 'if', 'else', 'orelse', 'or', 'and', 'while', 'for', 'switch', 'continue', 'break', 'catch',
+ 'try',
+ -- Not keyword but overly used variable name with always the same semantic.
+ 'self'
+}))
-- Types.
-local type = token(l.TYPE, word_match{
- 'enum', 'struct', 'union',
- 'i8', 'u8', 'i16', 'u16', 'i32', 'u32', 'i64', 'u64', 'i128', 'u128',
- 'isize', 'usize',
- 'c_short', 'c_ushort', 'c_int', 'c_uint',
- 'c_long', 'c_ulong', 'c_longlong', 'c_ulonglong', 'c_longdouble',
- 'c_void',
- 'f16', 'f32', 'f64', 'f128',
- 'bool',
- 'void',
- 'noreturn',
- 'type', 'anytype', 'error', 'anyerror',
- 'comptime_int', 'comptime_float',
-})
+lex:add_rule('type', token(lexer.TYPE, word_match{
+ 'enum', 'struct', 'union', --
+ 'i8', 'u8', 'i16', 'u16', 'i32', 'u32', 'i64', 'u64', 'i128', 'u128', --
+ 'isize', 'usize', --
+ 'c_short', 'c_ushort', 'c_int', 'c_uint', --
+ 'c_long', 'c_ulong', 'c_longlong', 'c_ulonglong', 'c_longdouble', --
+ 'c_void', --
+ 'f16', 'f32', 'f64', 'f128', --
+ 'bool', 'void', 'noreturn', 'type', 'anytype', 'error', 'anyerror', --
+ 'comptime_int', 'comptime_float'
+}))
-- Constants.
-local constant = token(l.CONSTANT, word_match{
- -- special values
- 'false', 'true', 'null', 'undefined',
-})
-
--- Identifiers.
-local identifier = token(l.IDENTIFIER, l.word)
+lex:add_rule('constant', token(lexer.CONSTANT, word_match{
+ -- Special values.
+ 'false', 'true', 'null', 'undefined'
+}))
-- Built-in functions.
-local functions = token(l.FUNCTION, word_match{
+lex:add_rule('function', token(lexer.FUNCTION, '@' * word_match{
'addWithOverflow', 'alignCast', 'alignOf', 'as', 'asyncCall', 'atomicLoad', 'atomicRmw',
'atomicStore', 'bitCast', 'bitOffsetOf', 'boolToInt', 'bitSizeOf', 'breakpoint', 'mulAdd',
'byteSwap', 'bitReverse', 'byteOffsetOf', 'call', 'cDefine', 'cImport', 'cInclude', 'clz',
'cmpxchgStrong', 'cmpxchgWeak', 'compileError', 'compileLog', 'ctz', 'cUndef', 'divExact',
- 'divFloor', 'divTrunc', 'embedFile', 'enumToInt', 'errorName', 'errorReturnTrace',
- 'errorToInt', 'errSetCast', 'export', 'fence', 'field', 'fieldParentPtr', 'floatCast',
- 'floatToInt', 'frame', 'Frame', 'frameAddress', 'frameSize', 'hasDecl', 'hasField', 'import',
- 'intCast', 'intToEnum', 'intToError', 'intToFloat', 'intToPtr', 'memcpy', 'memset', 'wasmMemorySize',
- 'wasmMemoryGrow', 'mod', 'mulWithOverflow', 'panic', 'popCount', 'ptrCast', 'ptrToInt', 'rem',
- 'returnAddress', 'setAlignStack', 'setCold', 'setEvalBranchQuota', 'setFloatMode', 'setRuntimeSafety',
- 'shlExact', 'shlWithOverflow', 'shrExact', 'shuffle', 'sizeOf', 'splat', 'reduce',
- 'src', 'sqrt', 'sin', 'cos', 'exp', 'exp2', 'log', 'log2', 'log10', 'fabs', 'floor',
- 'ceil', 'trunc', 'round', 'subWithOverflow', 'tagName', 'TagType', 'This', 'truncate',
- 'Type', 'typeInfo', 'typeName', 'TypeOf', 'unionInit',
-})
+ 'divFloor', 'divTrunc', 'embedFile', 'enumToInt', 'errorName', 'errorReturnTrace', 'errorToInt',
+ 'errSetCast', 'export', 'fence', 'field', 'fieldParentPtr', 'floatCast', 'floatToInt', 'frame',
+ 'Frame', 'frameAddress', 'frameSize', 'hasDecl', 'hasField', 'import', 'intCast', 'intToEnum',
+ 'intToError', 'intToFloat', 'intToPtr', 'memcpy', 'memset', 'wasmMemorySize', 'wasmMemoryGrow',
+ 'mod', 'mulWithOverflow', 'panic', 'popCount', 'ptrCast', 'ptrToInt', 'rem', 'returnAddress',
+ 'setAlignStack', 'setCold', 'setEvalBranchQuota', 'setFloatMode', 'setRuntimeSafety', 'shlExact',
+ 'shlWithOverflow', 'shrExact', 'shuffle', 'sizeOf', 'splat', 'reduce', 'src', 'sqrt', 'sin',
+ 'cos', 'exp', 'exp2', 'log', 'log2', 'log10', 'fabs', 'floor', 'ceil', 'trunc', 'round',
+ 'subWithOverflow', 'tagName', 'TagType', 'This', 'truncate', 'Type', 'typeInfo', 'typeName',
+ 'TypeOf', 'unionInit'
+}))
+-- Strings.
+local sq_str = P('L')^-1 * lexer.range("'", true)
+local dq_str = P('L')^-1 * lexer.range('"', true)
+lex:add_rule('string', token(lexer.STRING, sq_str + dq_str))
--- Operators.
-local operator = token(l.OPERATOR, S('+-/*%<>!=^&|?~:;,.()[]{}'))
+-- Identifiers.
+lex:add_rule('identifier', token(lexer.IDENTIFIER, lexer.word))
-M._rules = {
- {'whitespace', ws},
- {'keyword', keyword},
- {'constant', constant},
- {'function', functions},
- {'type', type},
- {'identifier', identifier},
- {'string', string},
- {'preprocessor', preprocessor},
- {'comment', comment},
- {'number', number},
- {'operator', operator},
-}
+-- Comments.
+lex:add_rule('doc_comment', token('doc_comment', lexer.to_eol('///', true)))
+lex:add_style('doc_comment', lexer.styles.comment)
+lex:add_rule('comment', token(lexer.COMMENT, lexer.to_eol('//', true)))
+
+-- Numbers.
+lex:add_rule('number', token(lexer.NUMBER, lexer.number))
+
+-- Operators.
+lex:add_rule('operator', token(lexer.OPERATOR, S('+-/*%<>!=^&|?~:;,.()[]{}')))
-M._foldsymbols = {
- _patterns = {'%l+', '[{}]', '/%*', '%*/', '//'},
- [l.OPERATOR] = {['{'] = 1, ['}'] = -1},
- [l.COMMENT] = {['//'] = l.fold_line_comments('//')}
-}
+-- Fold points.
+lex:add_fold_point(lexer.OPERATOR, '{', '}')
+lex:add_fold_point(lexer.COMMENT, lexer.fold_consecutive_lines('//'))
+lex:add_fold_point(lexer.PREPROCESSOR, lexer.fold_consecutive_lines('///'))
-return M
+return lex
You can read more about the author.