如果我有来自 AWS textract 方法（StartDocumentAnalysis）的 JobId 如何找到提取的文本？

Question

我这里有这个代码-

const _ = require("lodash");
const aws = require("aws-sdk");
const config = require("./config");

aws.config.update({
  accessKeyId: config.awsAccesskeyID,
  secretAccessKey: config.awsSecretAccessKey,
  region: config.awsRegion
});

const textract = new aws.Textract();

const getText = (result, blocksMap) => {
  let text = "";

  if (_.has(result, "Relationships")) {
    result.Relationships.forEach(relationship => {
      if (relationship.Type === "CHILD") {
        relationship.Ids.forEach(childId => {
          const word = blocksMap[childId];
          if (word.BlockType === "WORD") {
            text += `${word.Text} `;
          }
          if (word.BlockType === "SELECTION_ELEMENT") {
            if (word.SelectionStatus === "SELECTED") {
              text += `X `;
            }
          }
        });
      }
    });
  }

  return text.trim();
};

const findValueBlock = (keyBlock, valueMap) => {
  let valueBlock;
  keyBlock.Relationships.forEach(relationship => {
    if (relationship.Type === "VALUE") {
      relationship.Ids.every(valueId => {
        if (_.has(valueMap, valueId)) {
          valueBlock = valueMap[valueId];
          return false;
        }
      });
    }
  });

  return valueBlock;
};

const getKeyValueRelationship = (keyMap, valueMap, blockMap) => {
  const keyValues = {};
  console.log("Hello1");
  const keyMapValues = _.values(keyMap);

  keyMapValues.forEach(keyMapValue => {
    const valueBlock = findValueBlock(keyMapValue, valueMap);
    const key = getText(keyMapValue, blockMap);
    const value = getText(valueBlock, blockMap);
    keyValues[key] = value;
    console.log("Hello2");
  });

  return keyValues;
};

const getKeyValueMap = blocks => {
  const keyMap = {};
  const valueMap = {};
  const blockMap = {};
  console.log("Hello3");

  let blockId;
  blocks.forEach(block => {
    blockId = block.Id;
    blockMap[blockId] = block;
    console.log("Hello4");
    if (block.BlockType === "KEY_VALUE_SET") {
      if (_.includes(block.EntityTypes, "KEY")) {
        keyMap[blockId] = block;
        console.log("Hello5a");
      } else {
        valueMap[blockId] = block;
        console.log("Hello5b");
      }
    }
  });

  return { keyMap, valueMap, blockMap };
};


module.exports = async buffer => {
    const params = {
      DocumentLocation: {
        S3Object:{
            Bucket : "<data>",
            Name : "<data>"
        }
      },
      FeatureTypes: ["FORMS"]
    };





  const request = textract.startDocumentAnalysis(params);
  const params1 = {

    JobId : request.JobId

};
const request1 = textract.getDocumentAnalysis(params1);
  console.log("A");
  console.log(request1);
  console.log("A2");
  console.log(request1.Blocks);

        if(request1){
  console.log("B");

    console.log("C");

        console.log("D");

    const { keyMap, valueMap, blockMap } = getKeyValueMap(data1.Blocks);
    const keyValues = getKeyValueRelationship(keyMap, valueMap, blockMap);

    return keyValues;


  }

  return undefined;
};

现在我正在获取 JobId。这是一个异步操作。如何在不使用 AWS SNS 的情况下将此 JobId 传递到 getDocumentAnalysis 方法中？（作为试验，我还可以在我的代码中延迟所需的输出，作为 json 格式的提取词列表。但是我该如何处理那个？）

Answer 1

找到解决方案：使用 await 和 promise 构建代码并使用从异步函数返回的数据。

如果我有来自 AWS textract 方法（StartDocumentAnalysis）的 JobId 如何找到提取的文本？

If I have the JobId from AWS textract method(StartDocumentAnalysis) how to find the text extracted?

javascript

node.js

amazon-web-services

amazon-sns

amazon-textract