BigQuery 用户定义函数中的 Base64 编码

Question

BigQuery 将 Javascript 用于其用户定义的函数。 BigQuery 中BYTES 的输入和输出在Javascript 中映射到base64 编码的字符串。

BigQuery 没有浏览器 window 对象，因此缺少 atob 和 btoa。在 Bigquery JS 环境中是否有一种简单的编码和解码方法，或者您是否必须包含一个库来进行映射？

Answer 1

您需要包含一个库，但将 JavaScript 导入 Cloud Storage 后就相当简单了，您可以将这种方法用于您想要导入的其他常见库。我在a StackOverflow post找到了一个实现，我把这些内容放到了一个名为btoa_atob.js的文件中：

(function () {
  var chars = 'ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/=';

  function InvalidCharacterError(message) {
    this.message = message;
  }
  InvalidCharacterError.prototype = new Error;
  InvalidCharacterError.prototype.name = 'InvalidCharacterError';

  // encoder                                                                                                                                                                                                                                                                              
  // [https://gist.github.com/999166] by [https://github.com/nignag]                                                                                                                                                                                                                      
  btoa = function (input) {
    var str = String(input);
    for (
      // initialize result and counter                                                                                                                                                                                                                                                    
      var block, charCode, idx = 0, map = chars, output = '';
      // if the next str index does not exist:                                                                                                                                                                                                                                            
      //   change the mapping table to "="                                                                                                                                                                                                                                                
      //   check if d has no fractional digits                                                                                                                                                                                                                                            
      str.charAt(idx | 0) || (map = '=', idx % 1);
      // "8 - idx % 1 * 8" generates the sequence 2, 4, 6, 8                                                                                                                                                                                                                              
      output += map.charAt(63 & block >> 8 - idx % 1 * 8)
    ) {
      charCode = str.charCodeAt(idx += 3/4);
      if (charCode > 0xFF) {
        throw new InvalidCharacterError("'btoa' failed: The string to be encoded contains characters outside of the Latin1 range.");
      }
      block = block << 8 | charCode;
    }
    return output;
  };

  // decoder                                                                                                                                                                                                                                                                              
  // [https://gist.github.com/1020396] by [https://github.com/atk]                                                                                                                                                                                                                        
  atob = function (input) {
    var str = String(input).replace(/[=]+$/, ''); // #31: ExtendScript bad parse of /=                                                                                                                                                                                                    
    if (str.length % 4 == 1) {
      throw new InvalidCharacterError("'atob' failed: The string to be decoded is not correctly encoded.");
    }
    for (
      // initialize result and counters                                                                                                                                                                                                                                                   
      var bc = 0, bs, buffer, idx = 0, output = '';
      // get next character                                                                                                                                                                                                                                                               
      buffer = str.charAt(idx++);
      // character found in table? initialize bit storage and add its ascii value;                                                                                                                                                                                                        
      ~buffer && (bs = bc % 4 ? bs * 64 + buffer : buffer,
        // and if not first of each 4 characters,                                                                                                                                                                                                                                         
        // convert the first 8 bits to one ascii character                                                                                                                                                                                                                                
        bc++ % 4) ? output += String.fromCharCode(255 & bs >> (-2 * bc & 6)) : 0
    ) {
      // try to find character in table (0-63, not found => -1)                                                                                                                                                                                                                           
      buffer = chars.indexOf(buffer);
    }
    return output;
  };

}());

然后我将文件复制到我的云存储中：

gsutil cp btoa_atob.js gs://my-bucket/

然后我写了一个使用它的虚拟函数：

#standardSQL
CREATE TEMP FUNCTION Foo(b BYTES) RETURNS STRING LANGUAGE js AS """
var result = atob(b);
// ... process result of atob.
return result;
"""
OPTIONS (library='gs://my-bucket/btoa_atob.js');

SELECT Foo(b'\xa0b1\xff\xee');