@briancullen/aws-textract-parser
Version:
Library for converting AWS Textract responses into a more usable structure.
178 lines (177 loc) • 8.86 kB
JavaScript
;
var __awaiter = (this && this.__awaiter) || function (thisArg, _arguments, P, generator) {
function adopt(value) { return value instanceof P ? value : new P(function (resolve) { resolve(value); }); }
return new (P || (P = Promise))(function (resolve, reject) {
function fulfilled(value) { try { step(generator.next(value)); } catch (e) { reject(e); } }
function rejected(value) { try { step(generator["throw"](value)); } catch (e) { reject(e); } }
function step(result) { result.done ? resolve(result.value) : adopt(result.value).then(fulfilled, rejected); }
step((generator = generator.apply(thisArg, _arguments || [])).next());
});
};
var __generator = (this && this.__generator) || function (thisArg, body) {
var _ = { label: 0, sent: function() { if (t[0] & 1) throw t[1]; return t[1]; }, trys: [], ops: [] }, f, y, t, g;
return g = { next: verb(0), "throw": verb(1), "return": verb(2) }, typeof Symbol === "function" && (g[Symbol.iterator] = function() { return this; }), g;
function verb(n) { return function (v) { return step([n, v]); }; }
function step(op) {
if (f) throw new TypeError("Generator is already executing.");
while (_) try {
if (f = 1, y && (t = op[0] & 2 ? y["return"] : op[0] ? y["throw"] || ((t = y["return"]) && t.call(y), 0) : y.next) && !(t = t.call(y, op[1])).done) return t;
if (y = 0, t) op = [op[0] & 2, t.value];
switch (op[0]) {
case 0: case 1: t = op; break;
case 4: _.label++; return { value: op[1], done: false };
case 5: _.label++; y = op[1]; op = [0]; continue;
case 7: op = _.ops.pop(); _.trys.pop(); continue;
default:
if (!(t = _.trys, t = t.length > 0 && t[t.length - 1]) && (op[0] === 6 || op[0] === 2)) { _ = 0; continue; }
if (op[0] === 3 && (!t || (op[1] > t[0] && op[1] < t[3]))) { _.label = op[1]; break; }
if (op[0] === 6 && _.label < t[1]) { _.label = t[1]; t = op; break; }
if (t && _.label < t[2]) { _.label = t[2]; _.ops.push(op); break; }
if (t[2]) _.ops.pop();
_.trys.pop(); continue;
}
op = body.call(thisArg, _);
} catch (e) { op = [6, e]; y = 0; } finally { f = t = 0; }
if (op[0] & 5) throw op[1]; return { value: op[0] ? op[1] : void 0, done: true };
}
};
var __importDefault = (this && this.__importDefault) || function (mod) {
return (mod && mod.__esModule) ? mod : { "default": mod };
};
Object.defineProperty(exports, "__esModule", { value: true });
var factory_1 = __importDefault(require("./factory"));
/**
* This class provides methods to process the information returned by Textract into
* a tree structure that is easier to work with.
*
* A single instance of this class is automatically created for you and provided as
* the default export from this library.
*/
var TextractParser = /** @class */ (function () {
/** @hidden */
function TextractParser(factory) {
this.factory = factory;
}
/**
* Method that parses the textract response synchronously.
*
* For example it can also be used as part of processing the result of a promise
* as shown below.
*
* ```typescript
* textract.detectDocumentText(request).promise()
* .then(data => textractParser.parseDetectTextResponse(data))
* .then(parsedData => console.log(parsedData))
* .catch(err => console.log(err))
* ```
*
* **NOTE**: If used to process GetDocumentTextDetectionResponse response then all data should be
* contained within a single response. If a NextToken is detected on the response then null will
* be returned. See [[parseGetTextDetection]] for a helper method which will aggregate the
* responses from the GetDocumentTextDetection operation.
*
* @param response the response object returned from Textract or null if the response is incomplete
* @returns Document that acts as the root node for the processed tree
*/
TextractParser.prototype.parseDetectTextResponse = function (response) {
if (response.NextToken !== undefined) {
return null;
}
return this.factory.process(response);
};
/**
* Method that acts as a proxy for the standard Textract callback.
*
* This proxy will process the data returned by Textract and call the provided callback
* with the processed information. It can be invoked as shown, where myCallback is written
* by the user of the library.
*
* ```typescript
* textract.detectDocumentText(request, textractParser.parseDetectTextCallback(myCallback))
* ```
*
* @param callback the callback to be invoked with the processed data or error
* @returns callback function that can be used with the AWS Textract invocation
*/
TextractParser.prototype.parseDetectTextCallback = function (callback) {
var _this = this;
return function (err, detectTextResponse) {
if (err !== null || detectTextResponse === null) {
callback(err, null);
}
else {
callback(null, _this.parseDetectTextResponse(detectTextResponse));
}
};
};
/**
* Method that retrieves the result of a asynchronous document text detection operation
* (which may require multiple requests to AWS) and produces a tree of the results.
*
* An example of how to use this method is shown below.
*
* ```typescript
* const jobId = 'your-job-id'
* const client = new AWS.Textract()
*
* textract.detectDocumentText(client, jobId)
* .then(parsedData => console.log(parsedData))
* .catch(err => console.log(err))
* ```
*
* If the specified Textract job is not marked as SUCCEEDED or the AWS operations fail
* to return the results then the Promise will be rejected.
*
* **NOTE**: This method will try and retrieve all the results for the Textract job and
* process them in memory. For extremely large documents then memory may become an issue.
*
* @param client the AWS client to use for retrieving the Textract results
* @param jobId the id of the Textract job for which we want to parse the results
* @returns Promise for a document that acts as the root node for the processed tree
*/
TextractParser.prototype.parseGetTextDetection = function (textract, jobId) {
return __awaiter(this, void 0, void 0, function () {
var _this = this;
return __generator(this, function (_a) {
return [2 /*return*/, this.getGetTextDetectionResponse(textract, jobId)
.then(function (request) { return _this.factory.process(request); })];
});
});
};
/** @hidden */
TextractParser.prototype.getGetTextDetectionResponse = function (textract, jobId, nextToken) {
return __awaiter(this, void 0, void 0, function () {
var _this = this;
return __generator(this, function (_a) {
return [2 /*return*/, textract.getDocumentTextDetection({ JobId: jobId, NextToken: nextToken }).promise()
.then(function (response) {
if (response.JobStatus !== 'SUCCEEDED') {
throw new Error("Job status is " + response.JobStatus + " only SUCCEEDED jobs can be processed");
}
else if (response.NextToken !== undefined) {
return _this.getGetTextDetectionResponse(textract, jobId, response.NextToken)
.then(function (otherResponse) {
var _a, _b;
return {
DocumentMetadata: response.DocumentMetadata,
Blocks: (_a = response.Blocks, (_a !== null && _a !== void 0 ? _a : [])).concat((_b = otherResponse.Blocks, (_b !== null && _b !== void 0 ? _b : [])))
};
});
}
else {
return response;
}
})];
});
});
};
return TextractParser;
}());
exports.TextractParser = TextractParser;
var types_1 = require("./types");
exports.BlockType = types_1.BlockType;
var Geometry_1 = require("./model/Geometry");
exports.Geometry = Geometry_1.Geometry;
exports.BoundaryBox = Geometry_1.BoundaryBox;
exports.Point = Geometry_1.Point;
exports.default = new TextractParser(factory_1.default);