to utf-8

自动转换编码.rb

def txt_to_utf(file)
  open(file) do |f|
    s = f.read
    #shift_jis 必须写在前面，因为被误判为gbk的概率很高
    x = %w(shift_jis gbk big5)
    begin
      u = s.dup.encode("utf-8",x.shift)
    rescue Encoding::UndefinedConversionError,Encoding::InvalidByteSequenceError => ex
      if x.empty? 
        if s.chr.ord.to_s(16) == "efbb"
          #处理utf-8 with bom 文件
        end
      else
        retry
      end
    else
      #处理 shift-jis, gbk, big5 文件
    end
  end
end