Question

我正在为Lua运行Windows CE 6/7的移动设备编写一个grep实用程序，但我遇到了一些实现不区分大小写的匹配模式的问题。将所有内容转换为大写（或更低）的明显解决方案由于字符类而无法正常工作。

我唯一能想到的是将模式本身的文字转换为大写。

这是我到目前为止所拥有的：

function toUpperPattern(instr)
    -- Check first character
    if string.find(instr, "^%l") then
        instr = string.upper(string.sub(instr, 1, 1)) .. string.sub(instr, 2)
    end
    -- Check the rest of the pattern
    while 1 do
        local a, b, str = string.find(instr, "[^%%](%l+)")
        if not a then break end
        if str then
            instr = string.sub(instr, 1, a) .. string.upper(string.sub(instr, a+1, b)) .. string.sub(instr, b + 1)
        end
    end
    return instr
end

我不想承认到目前为止需要多长时间，我仍然可以立即看到像逃脱百分号'%%'这样的问题

我认为这一定是一个相当普遍的问题，但我似乎无法在这个主题上找到太多。有没有更简单（或至少完整）的方法来做到这一点？我在这里开始变得疯狂...... 希望你那里的Lua大师可以启发我！

Answer 1

尝试这样的事情：

function case_insensitive_pattern(pattern)

  -- find an optional '%' (group 1) followed by any character (group 2)
  local p = pattern:gsub("(%%?)(.)", function(percent, letter)

    if percent ~= "" or not letter:match("%a") then
      -- if the '%' matched, or `letter` is not a letter, return "as is"
      return percent .. letter
    else
      -- else, return a case-insensitive character class of the matched letter
      return string.format("[%s%s]", letter:lower(), letter:upper())
    end

  end)

  return p
end

print(case_insensitive_pattern("xyz = %d+ or %% end"))

打印：

[xX][yY][zZ] = %d+ [oO][rR] %% [eE][nN][dD]

Answer 2

Lua 5.1，LPeg v0.12

do
    local p = re.compile([[
        pattern  <- ( {b} / {escaped} / brackets / other)+
        b        <- "%b" . .
        escaped  <- "%" .
        brackets <- { "[" ([^]%]+ / escaped)* "]" }
        other    <- [^[%]+ -> cases
    ]], {
        cases = function(str) return (str:gsub('%a',function(a) return '['..a:lower()..a:upper()..']' end)) end
    })
    local pb = re.compile([[
        pattern  <- ( {b} / {escaped} / brackets / other)+
        b        <- "%b" . .
        escaped  <- "%" .
        brackets <- {: {"["} ({escaped} / bcases)* {"]"} :}
        bcases   <- [^]%]+ -> bcases
        other    <- [^[%]+ -> cases
    ]], {
        cases = function(str) return (str:gsub('%a',function(a) return '['..a:lower()..a:upper()..']' end)) end
        , bcases = function(str) return (str:gsub('%a',function(a) return a:lower()..a:upper() end)) end
    })
    function iPattern(pattern,brackets)
        ('sanity check'):find(pattern)
        return table.concat({re.match(pattern, brackets and pb or p)})
    end
end

local test                  = '[ab%c%]d%%]+ o%%r %bnm'
print(iPattern(test))       -- [ab%c%]d%%]+ [oO]%%[rR] %bnm
print(iPattern(test,true))  -- [aAbB%c%]dD%%]+ [oO]%%[rR] %bnm
print(('qwe [%D]% O%r n---m asd'):match(iPattern(test, true))) -- %D]% O%r n---m

Pure Lua版本：

有必要分析字符串中的所有字符以将其转换为正确的模式，因为Lua模式没有像regexps（abc | something）那样的替换。

function iPattern(pattern, brackets)
    ('sanity check'):find(pattern)
    local tmp = {}
    local i=1
    while i <= #pattern do              -- 'for' don't let change counter
        local char = pattern:sub(i,i)   -- current char
        if char == '%' then
            tmp[#tmp+1] = char          -- add to tmp table
            i=i+1                       -- next char position
            char = pattern:sub(i,i)
            tmp[#tmp+1] = char
            if char == 'b' then         -- '%bxy' - add next 2 chars
                tmp[#tmp+1] = pattern:sub(i+1,i+2)
                i=i+2
            end
        elseif char=='[' then           -- brackets
            tmp[#tmp+1] = char
            i = i+1
            while i <= #pattern do
                char = pattern:sub(i,i)
                if char == '%' then     -- no '%bxy' inside brackets
                    tmp[#tmp+1] = char
                    tmp[#tmp+1] = pattern:sub(i+1,i+1)
                    i = i+1
                elseif char:match("%a") then    -- letter
                    tmp[#tmp+1] = not brackets and char or char:lower()..char:upper()
                else                            -- something else
                    tmp[#tmp+1] = char
                end
                if char==']' then break end -- close bracket
                i = i+1
            end
        elseif char:match("%a") then    -- letter
            tmp[#tmp+1] = '['..char:lower()..char:upper()..']'
        else
            tmp[#tmp+1] = char          -- something else
        end
        i=i+1
    end
    return table.concat(tmp)
end

local test                  = '[ab%c%]d%%]+ o%%r %bnm'
print(iPattern(test))       -- [ab%c%]d%%]+ [oO]%%[rR] %bnm
print(iPattern(test,true))  -- [aAbB%c%]dD%%]+ [oO]%%[rR] %bnm
print(('qwe [%D]% O%r n---m asd'):match(iPattern(test, true))) -- %D]% O%r n---m

不区分大小写的Lua模式匹配

2 个答案: