我正在执行一个简单的功能,该功能应该从阿拉伯文本中删除tashkeel,替换技术适用于英语,但不适用于阿拉伯语,您会提出什么建议?

lua代码:-

function replacePartOfString(arg,old,new)
  local zzz = arg.gsub(arg, old, new)
  return zzz
end

function wordLengthIgnoringTashkeel(arg)
  local tashkeelArray = {"َ","ً","ُ","ٌ","ِ","ٍ","ْ","َ"}

  local tempWord = arg

  print("tempWord Before"..tempWord)
  for x=1,#tashkeelArray do
      replacePartOfString(tempWord,tashkeelArray[x],"")
  end
  print("tempWord After"..tempWord)
end

结果

tempWord After اليَوْمَ tempWord After اليَوْمَ

而预期的结果

预期结果

tempWord之后اليَوْمْ tempWord之后اليَوَمَ

最佳答案

这有效

function replacePartOfString(arg,old,new)
  return arg.gsub(arg, old, new)
end

function wordLengthIgnoringTashkeel(arg)
  local tashkeelArray = {"َ","ً","ُ","ٌ","ِ","ٍ","ْ","َّ"}
  local tempWord = arg
  for x=1,#tashkeelArray do
      tempWord = replacePartOfString(tempWord,tashkeelArray[x],"")
  end
  return #tempWord
end

10-04 19:05