字符串插值
 |
||
|
字符串插值 |
|
print("Hello " .. name .. ", the value of key " .. k .. " is " .. v .. "!")
与 Perl 相比，Perl 中变量可以嵌入到字符串中
print "Hello $name, the value of key $k is $b!\n";
关于 Lua 的抱怨是其引用方式冗长，并且可能更难阅读，例如在视觉上区分哪些文本在引号内或引号外。除了使用带有语法高亮显示的编辑器外，后者问题可以通过括号引用风格来改善
print([[Hello ]] .. name .. [[, the value of key ]] .. k .. [[ is ]] .. v .. [[!]])
使用 string.format 也可以使其更简洁
print(string.format("Hello %s, the value of key %s is %s", name, k, v))
可能使用一个辅助函数
function printf(...) print(string.format(...)) end printf("Hello %s, the value of key %s is %s", name, k, v)
这带来的新问题是变量是按位置标识的，如果变量数量很多，会带来可读性和可维护性问题。
以下解决方案展示了如何在 Lua 中实现支持将变量插值到字符串中，以达到类似如下的语法
printf("Hello %(name), the value of key %(k) is %(v)")
这是一个简单的实现（-- RiciLake）
function interp(s, tab) return (s:gsub('($%b{})', function(w) return tab[w:sub(3, -2)] or w end)) end print( interp("${name} is ${value}", {name = "foo", value = "bar"}) ) getmetatable("").__mod = interp print( "${name} is ${value}" % {name = "foo", value = "bar"} ) -- Outputs "foo is bar"
这是另一个实现（-- RiciLake），支持 Pythonic 格式化规范（需要 Lua 5.1 或更高版本）
function interp(s, tab) return (s:gsub('%%%((%a%w*)%)([-0-9%.]*[cdeEfgGiouxXsq])', function(k, fmt) return tab[k] and ("%"..fmt):format(tab[k]) or '%('..k..')'..fmt end)) end getmetatable("").__mod = interp print( "%(key)s is %(val)7.2f%" % {key = "concentration", val = 56.2795} ) -- outputs "concentration is 56.28%"
这是另一个仅限 Lua 的解决方案（-- MarkEdgar）
function replace_vars(str, vars) -- Allow replace_vars{str, vars} syntax as well as replace_vars(str, {vars}) if not vars then vars = str str = vars[1] end return (string_gsub(str, "({([^}]+)})", function(whole,i) return vars[i] or whole end)) end -- Example: output = replace_vars{ [[Hello {name}, welcome to {company}. ]], name = name, company = get_company_name() }
Ruby 和 Python 都为字符串格式化提供了一种简写形式，使用 % 运算符。
下面的代码片段向 Lua 添加了类似的模运算符用法
getmetatable("").__mod = function(a, b) if not b then return a elseif type(b) == "table" then return string.format(a, unpack(b)) else return string.format(a, b) end end
用法示例
print( "%5.2f" % math.pi ) print( "%-10.10s %04d" % { "test", 123 } )
你可能喜欢或不喜欢这种表示法，自行选择。
下面是一个更复杂的实现（-- DavidManura）。它利用 debug 库（特别是 debug.getlocal()）来查询局部变量，这可能出于多种原因而不可取（-- RiciLake）。首先，它可以用于中断你不应该中断的事情，所以如果运行受信任的代码，这是一个坏主意。debug.getlocal()也很昂贵，因为它需要扫描整个字节码来确定哪些变量在作用域内。它也不会捕获闭包变量。
代码
-- "nil" value that can be stored in tables. local mynil_mt = {__tostring = function() return tostring(nil) end} local mynil = setmetatable({}, mynil_mt) -- Retrieves table of all local variables (name, value) -- in given function <func>. If a value is Nil, it instead -- stores the value <mynil> in the table to distinguish a -- a local variable that is nil from the local variable not -- existing. -- If a number is given in place of <func>, then it -- uses that level in the call stack. Level 1 is the -- function that called get_locals. -- Note: this correctly handles the case where two locals have the -- same name: "local x = 1 ... get_locals(1) ... local x = 2". -- This function is similar and is based on debug.getlocal(). function get_locals(func) local n = 1 local locals = {} func = (type(func) == "number") and func + 1 or func while true do local lname, lvalue = debug.getlocal(func, n) if lname == nil then break end -- end of list if lvalue == nil then lvalue = mynil end -- replace locals[lname] = lvalue n = n + 1 end return locals end -- Interpolates variables into string <str>. -- Variables are defined in table <table>. If <table> is -- omitted, then it uses local and global variables in the -- calling function. -- Option level indicates the level in the call stack to -- obtain local variable from (1 if omitted). function interp(str, table, level) local use_locals = (table == nil) table = table or getfenv(2) if use_locals then level = level or 1 local locals = get_locals(level + 1) table = setmetatable(locals, {__index = table}) end local out = string.gsub(str, '$(%b{})', function(w) local variable_name = string.sub(w, 2, -2) local variable_value = table[variable_name] if variable_value == mynil then variable_value = nil end return tostring(variable_value) end ) return out end -- Interpolating print. -- This is just a wrapper around print and interp. -- It only accepts a single string argument. function printi(str) print(interp(str, nil, 2)) end -- Pythonic "%" operator for srting interpolation. getmetatable("").__mod = interp
测试
-- test globals x=123 assert(interp "x = ${x}" == "x = 123") -- test table assert(interp("x = ${x}", {x = 234}) == "x = 234") -- test locals (which override globals) do local x = 3 assert(interp "x = ${x}" == "x = 3") end -- test globals using setfenv function test() assert(interp "y = ${y}" == "y = 123") end local env = {y = 123} setmetatable(env, {__index = _G}) setfenv(test, env) test() -- test of multiple locals of same name do local z = 1 local z = 2 assert(interp "z = ${z}" == "z = 2") local z = 3 end -- test of locals with nil value do z = 2 local z = 1 local z = nil assert(interp "z = ${z}" == "z = nil") end -- test of printi x = 123 for k, v in ipairs {3,4} do printi("${x} - The value of key ${k} is ${v}") end -- test of "%" operator assert("x = ${x}" % {x = 2} == "x = 2")
可以进行各种改进。例如，
v = {x = 2}
print(interp "v.x = ${v.x}") -- not implemented
我在 Ruby 和 PHP 中喜欢的特性之一是能够将变量包含在字符串中，例如 print "Hello ${Name}" 下面的补丁做了同样的事情，但仅限于 doc string 类型，即以 [[ 开头并以 ]] 结尾的字符串。它使用 "|" 字符来表示花括号的开闭。
要内联添加变量，例如
output = [[Hello |name|, welcome to |get_company_name()|. ]]
补丁所做的就是字面意思上将上面的内容转换为
output = [[Hello ]]..name..[[, welcome to ]]..get_company_name()..[[. ]]
llex.c 文件中更新了以下函数。
重要提示： 不知何故，我需要另一个字符来表示代码中的闭合花括号，并且我随意选择了 ''，这意味着如果你在字符串中有该字符（尤其是在使用外语编码时），你将得到一个语法错误。我不知道目前是否有解决方案。
int luaX_lex (LexState *LS, SemInfo *seminfo) {
for (;;) {
switch (LS->current) {
case '\n': {
inclinenumber(LS);
continue;
}
case '-': {
next(LS);
if (LS->current != '-') return '-';
/* else is a comment */
next(LS);
if (LS->current == '[' && (next(LS), LS->current == '['))
read_long_string(LS, NULL); /* long comment */
else /* short comment */
while (LS->current != '\n' && LS->current != EOZ)
next(LS);
continue;
}
case '[': {
next(LS);
if (LS->current != '[') return '[';
else {
read_long_string(LS, seminfo);
return TK_STRING;
}
}
case '=': {
next(LS);
if (LS->current != '=') return '=';
else { next(LS); return TK_EQ; }
}
case '<': {
next(LS);
if (LS->current != '=') return '<';
else { next(LS); return TK_LE; }
}
case '>': {
next(LS);
if (LS->current != '=') return '>';
else { next(LS); return TK_GE; }
}
case '~': {
next(LS);
if (LS->current != '=') return '~';
else { next(LS); return TK_NE; }
}
case '"':
case '\'': {
read_string(LS, LS->current, seminfo);
return TK_STRING;
}
// added!!!
//------------------------------
case '|': {
LS->current = '�';
return TK_CONCAT;
}
case '�': {
read_long_string(LS, seminfo);
return TK_STRING;
}
//------------------------------
case '.': {
next(LS);
if (LS->current == '.') {
next(LS);
if (LS->current == '.') {
next(LS);
return TK_DOTS; /* ... */
}
else return TK_CONCAT; /* .. */
}
else if (!isdigit(LS->current)) return '.';
else {
read_numeral(LS, 1, seminfo);
return TK_NUMBER;
}
}
case EOZ: {
return TK_EOS;
}
default: {
if (isspace(LS->current)) {
next(LS);
continue;
}
else if (isdigit(LS->current)) {
read_numeral(LS, 0, seminfo);
return TK_NUMBER;
}
else if (isalpha(LS->current) || LS->current == '_') {
/* identifier or reserved word */
size_t l = readname(LS);
TString *ts = luaS_newlstr(LS->L, luaZ_buffer(LS->buff), l);
if (ts->tsv.reserved > 0) /* reserved word? */
return ts->tsv.reserved - 1 + FIRST_RESERVED;
seminfo->ts = ts;
return TK_NAME;
}
else {
int c = LS->current;
if (iscntrl(c))
luaX_error(LS, "invalid control char",
luaO_pushfstring(LS->L, "char(%d)", c));
next(LS);
return c; /* single-char tokens (+ - / ...) */
}
}
}
}
}
static void read_long_string (LexState *LS, SemInfo *seminfo) {
int cont = 0;
size_t l = 0;
checkbuffer(LS, l);
save(LS, '[', l); /* save first `[' */
save_and_next(LS, l); /* pass the second `[' */
if (LS->current == '\n') /* string starts with a newline? */
inclinenumber(LS); /* skip it */
for (;;) {
checkbuffer(LS, l);
switch (LS->current) {
case EOZ:
save(LS, '\0', l);
luaX_lexerror(LS, (seminfo) ? "unfinished long string" :
"unfinished long comment", TK_EOS);
break; /* to avoid warnings */
case '[':
save_and_next(LS, l);
if (LS->current == '[') {
cont++;
save_and_next(LS, l);
}
continue;
case ']':
save_and_next(LS, l);
if (LS->current == ']') {
if (cont == 0) goto endloop;
cont--;
save_and_next(LS, l);
}
continue;
// added
//------------------------------
case '|':
save(LS, ']', l);
LS->lookahead.token = TK_CONCAT;
goto endloop;
continue;
//------------------------------
case '\n':
save(LS, '\n', l);
inclinenumber(LS);
if (!seminfo) l = 0; /* reset buffer to avoid wasting space */
continue;
default:
save_and_next(LS, l);
}
} endloop:
save_and_next(LS, l); /* skip the second `]' */
save(LS, '\0', l);
if (seminfo)
seminfo->ts = luaS_newlstr(LS->L, luaZ_buffer(LS->buff) + 2, l - 5);
}
--Sam Lie
对于 MetaLua 实现，请参阅 MetaLuaRecipes 中的“字符串插值”。
请参阅 [gist1338609]（--DavidManura），它安装了一个自定义搜索器函数，用于预处理正在加载的模块。提供的示例预处理器进行字符串插值
--! code = require 'interpolate' (code) local M = {} local function printf(s, ...) local vals = {...} local i = 0 s = s:gsub('\0[^\0]*\0', function() i = i + 1 return tostring(vals[i]) end) print(s) end function M.test() local x = 16 printf("value is $(math.sqrt(x)) ") end return M
f"$(x) $(y)" 成为 f("$(x) $(y)",x,y) 的语法糖
在字符串中嵌入表达式可以有这些应用