From 08edd2303544ba321ae8969dd28b115f305d6246 Mon Sep 17 00:00:00 2001 From: Vanic Date: Sat, 17 Jan 2026 22:24:37 +0300 Subject: [PATCH] Fix warning EmmyLua. Close #1 --- init.lua | 143 ++++++++++++++++++++++++++++++------------------------- 1 file changed, 79 insertions(+), 64 deletions(-) diff --git a/init.lua b/init.lua index 9b640b7..774ef60 100644 --- a/init.lua +++ b/init.lua @@ -18,26 +18,28 @@ end local utf8charpattern = '[%z\1-\127\194-\244][\128-\191]*' ---- Determines the length of a character in bytes encoded in UTF-8, based on the first byte of the character. ---- @param byte number First byte of a character. ---- @return number +---Determines the length of a character in bytes encoded in UTF-8, based on the first byte of the character. +---@param byte number First byte of a character. +---@return integer local function utf8symbollen(byte) ensureArgType(byte, "number", 1, "utf8symbollen") return not byte and 0 or (byte < 0x80 and 1) or (byte >= 0xF0 and 4) or (byte >= 0xE0 and 3) or (byte >= 0xC0 and 2) or 1 end +---@type table local head_table = {} for i = 0, 255 do head_table[i] = utf8symbollen(i) end + head_table[256] = 0 ---- Returns the length of the character in bytes starting at position `pos` in the string `str` using the table `head_table`. ---- @param str string Input string. ---- @param bs number Position of character in line. ---- @return number +---Returns the length of the character in bytes starting at position `pos` in the string `str` using the table `head_table`. +---@param str string Input string. +---@param bs integer Position of character in line. +---@return integer local function utf8charbytes(str, bs) ensureArgType(str, "string", 1, "utf8charbytes") ensureArgType(bs, "number", 2, "utf8charbytes") @@ -47,10 +49,10 @@ local function utf8charbytes(str, bs) return head_table[byte(str, bs) or 256] end ---- Returns the new position in the string `str`, skipping the current character. ---- @param str string Input string. ---- @param bs number Position of character in line. ---- @return number +---Returns the new position in the string `str`, skipping the current character. +---@param str string Input string. +---@param bs integer Position of character in line. +---@return integer local function utf8next(str, bs) ensureArgType(str, "string", 1, "utf8next") ensureArgType(bs, "number", 2, "utf8next") @@ -60,9 +62,9 @@ local function utf8next(str, bs) return bs + utf8charbytes(str, bs) end ---- Returns the number of characters in a UTF-8 string ---- @param str string Input string. ---- @return number +---Returns the number of characters in a UTF-8 string +---@param str string Input string. +---@return integer function string_utf8.len(str) ensureArgType(str, "string", 1, "string_utf8.len") @@ -81,12 +83,12 @@ function string_utf8.len(str) end ---- Functions identically to `string.sub` except that `i` and `j` are UTF-8 characters instead of bytes. ---- @param str string Input string. ---- @param i number The starting character index (default: 1). Negative values count from the end. ---- @param j number The ending character index (default: i). Negative values count from the end. ---- @overload fun(s: string, i: number) ---- @return string +---Functions identically to `string.sub` except that `i` and `j` are UTF-8 characters instead of bytes. +---@param str string Input string. +---@param i integer The starting character index (default: 1). Negative values count from the end. +---@param j integer The ending character index (default: i). Negative values count from the end. +---@overload fun(s: string, i: integer) +---@return string function string_utf8.sub(str, i, j) j = j or -1 @@ -129,15 +131,14 @@ function string_utf8.sub(str, i, j) return sub(str, start, finish) end ---- Returns a UTF-8 string from the given Unicode codes. ---- @param ... number List of Unicode codes. ---- @return string +---Returns a UTF-8 string from the given Unicode codes. +---@param ... integer List of Unicode codes. +---@return string function string_utf8.char(...) local codes = {...} assert(codes ~= {}, 'bad argument #1 to \'string_utf8.char\' (key cannot be nil)') - --- @type int[] local result = {} for _, unicode in ipairs(codes) do @@ -183,11 +184,11 @@ local shift_6 = 16 -- 2^6 local shift_12 = 4096 -- 2^12 local shift_18 = 262144 -- 2^18 ---- Converts UTF-8 encoded characters in a string to their corresponding Unicode code points. ---- @param str string The input string containing UTF-8 encoded characters. ---- @param ibs number The starting byte position in the string (inclusive). ---- @param jbs number The ending byte position in the string (inclusive). ---- @return number | number... +---Converts UTF-8 encoded characters in a string to their corresponding Unicode code points. +---@param str string The input string containing UTF-8 encoded characters. +---@param ibs integer The starting byte position in the string (inclusive). +---@param jbs integer The ending byte position in the string (inclusive). +---@return integer... function string_utf8.unicode(str, ibs, jbs) ensureArgType(str, "string", 1, "string_utf8.unicode") ensureArgType(ibs, "number", 2, "string_utf8.unicode") @@ -201,12 +202,15 @@ function string_utf8.unicode(str, ibs, jbs) bytes = utf8charbytes(str, ibs) if bytes == 0 then return end + ---@type integer local unicode if bytes == 1 then unicode = byte(str, ibs, ibs) end if bytes == 2 then + ---@type integer, integer local byte0,byte1 = byte(str, ibs, ibs + 1) if byte0 and byte1 then + ---@type integer, integer local code0,code1 = byte0-0xC0,byte1-0x80 unicode = code0*shift_6 + code1 else @@ -214,8 +218,10 @@ function string_utf8.unicode(str, ibs, jbs) end end if bytes == 3 then + ---@type integer, integer, integer local byte0,byte1,byte2 = byte(str, ibs, ibs + 2) if byte0 and byte1 and byte2 then + ---@type integer, integer, integer local code0,code1,code2 = byte0-0xE0,byte1-0x80,byte2-0x80 unicode = code0*shift_12 + code1*shift_6 + code2 else @@ -223,8 +229,10 @@ function string_utf8.unicode(str, ibs, jbs) end end if bytes == 4 then + ---@type integer, integer, integer, integer local byte0,byte1,byte2,byte3 = byte(str, ibs, ibs + 3) if byte0 and byte1 and byte2 and byte3 then + ---@type integer, integer, integer, integer local code0,code1,code2,code3 = byte0-0xF0,byte1-0x80,byte2-0x80,byte3-0x80 unicode = code0*shift_18 + code1*shift_12 + code2*shift_6 + code3 else @@ -239,13 +247,13 @@ function string_utf8.unicode(str, ibs, jbs) end end ---- Returns Unicode code points for characters in a UTF-8 string within the specified range. ---- @param str string The input UTF-8 encoded string. ---- @param i number The starting character index (default: 1). Negative values count from the end. ---- @param j number The ending character index (default: i). Negative values count from the end. ---- @overload fun(str: string) ---- @overload fun(str: string, i: number) ---- @return number | number... +---Returns Unicode code points for characters in a UTF-8 string within the specified range. +---@param str string The input UTF-8 encoded string. +---@param i integer The starting character index (default: 1). Negative values count from the end. +---@param j integer The ending character index (default: i). Negative values count from the end. +---@overload fun(str: string) +---@overload fun(str: string, i: number) +---@return integer... function string_utf8.byte(str, i, j) ensureArgType(str, "string", 1, "string_utf8.byte") ensureArgType(i, "number", 2, "string_utf8.byte") @@ -279,7 +287,7 @@ function string_utf8.byte(str, i, j) end if not ibs or not jbs then - return nil + return end else ibs, jbs = 1, 1 @@ -288,10 +296,10 @@ function string_utf8.byte(str, i, j) return string_utf8.unicode(str, ibs, jbs) end ---- Creates an iterator to generate UTF-8 substrings of a specified length. ---- @param str string The input UTF-8 encoded string. ---- @param sub_len? number The length of each substring in characters (default: 1). ---- @return fun(skip_ptr: table | nil, bs: number | nil) +---Creates an iterator to generate UTF-8 substrings of a specified length. +---@param str string The input UTF-8 encoded string. +---@param sub_len integer? The length of each substring in characters (default: 1). +---@return fun(skip_ptr: table | nil, bs: integer | nil) function string_utf8.gensub(str, sub_len) sub_len = sub_len or 1 @@ -302,6 +310,8 @@ function string_utf8.gensub(str, sub_len) local max_len = #str + ---@param skip_ptr table + ---@param bs integer return function(skip_ptr, bs) bs = (bs and bs or 1) + (skip_ptr and (skip_ptr[1] or 0) or 0) @@ -315,9 +325,9 @@ function string_utf8.gensub(str, sub_len) end end ---- Reverses a UTF-8 encoded string while preserving multi-byte characters. ---- @param str string The input UTF-8 encoded string. ---- @return string +---Reverses a UTF-8 encoded string while preserving multi-byte characters. +---@param str string The input UTF-8 encoded string. +---@return string function string_utf8.reverse(str) ensureArgType(str, "string", 1, "string_utf8.reverse") @@ -330,11 +340,11 @@ function string_utf8.reverse(str) return result end ---- Validates UTF-8 encoded characters in a string starting from a given byte position. ---- @param str string The input UTF-8 encoded string to validate. ---- @param bs number The starting byte position for validation (default: 1). ---- @overload fun(str: string) ---- @return number? +---Validates UTF-8 encoded characters in a string starting from a given byte position. +---@param str string The input UTF-8 encoded string to validate. +---@param bs integer The starting byte position for validation (default: 1). +---@overload fun(str: string) +---@return integer?, integer?, integer?, integer? local function utf8validator(str, bs) bs = bs or 1 @@ -354,7 +364,8 @@ local function utf8validator(str, bs) return bs + 1 elseif c >= 128 and c <= 193 then return bs + 1, bs, 1, c - -- UTF8-2 + + -- UTF8-2 elseif c >= 194 and c <= 223 then local c2 = byte(str, bs + 1) if not c2 or c2 < 128 or c2 > 191 then @@ -362,8 +373,10 @@ local function utf8validator(str, bs) end return bs + 2 - -- UTF8-3 + + -- UTF8-3 elseif c >= 224 and c <= 239 then + ---@type integer? local c2 = byte(str, bs + 1) if not c2 then @@ -387,6 +400,7 @@ local function utf8validator(str, bs) return bs + 3 -- UTF8-4 elseif c >= 240 and c <= 244 then + ---@type integer? local c2 = byte(str, bs + 1) if not c2 then @@ -418,10 +432,10 @@ local function utf8validator(str, bs) end end ---- Validates a UTF-8 encoded string for correctness. ---- @param str string The input UTF-8 encoded string to validate. ---- @param byte_pos? number The starting byte position for validation (default: 1). ---- @return boolean | table +---Validates a UTF-8 encoded string for correctness. +---@param str string The input UTF-8 encoded string to validate. +---@param byte_pos? integer The starting byte position for validation (default: 1). +---@return boolean, table function string_utf8.validate(str, byte_pos) byte_pos = byte_pos or 1 @@ -437,12 +451,13 @@ function string_utf8.validate(str, byte_pos) result[#result + 1] = { pos = bs, part = part, code = code } end end + return #result == 0, result end ---- Creates an iterator to traverse UTF-8 encoded characters in a string. ---- @param str string The input UTF-8 encoded string. ---- @return fun(skip_ptr: table|nil) +---Creates an iterator to traverse UTF-8 encoded characters in a string. +---@param str string The input UTF-8 encoded string. +---@return fun(skip_ptr: table|nil) function string_utf8.codes(str) ensureArgType(str, "string", 1, "string_utf8.codes") @@ -476,12 +491,12 @@ n > 0: n jumps forward n < 0: n more scans backwards --]] ---- Finds the byte position of the `n`-th UTF-8 character in a string, starting from a given byte position. ---- @param str string The input UTF-8 encoded string. ---- @param n number The character index to find. If `n` is negative, counts from the end. ---- @param bs number The starting byte position (default: 1 for positive `n`, end of string for negative `n`). ---- @overload fun(str: string, n: number) ---- @return number | nil +---Finds the byte position of the `n`-th UTF-8 character in a string, starting from a given byte position. +---@param str string The input UTF-8 encoded string. +---@param n integer The character index to find. If `n` is negative, counts from the end. +---@param bs integer The starting byte position (default: 1 for positive `n`, end of string for negative `n`). +---@overload fun(str: string, n: number) +---@return number | nil function string_utf8.offset(str, n, bs) local l = #str if not bs then