@pdftron/pdfnet-node-samples 9.4.2 → 9.5.0-2-beta-1

package/samples/DataExtractionTest/DataExtractionTest.js

@@ -0,0 +1,180 @@
+//---------------------------------------------------------------------------------------
+// Copyright (c) 2001-2023 by PDFTron Systems Inc. All Rights Reserved.
+// Consult legal.txt regarding legal and license information.
+//---------------------------------------------------------------------------------------
+
+//---------------------------------------------------------------------------------------
+// The Data Extraction suite is an optional PDFNet add-on collection that can be used to
+// extract various types of data from PDF documents.
+//
+// The PDFTron SDK Data Extraction suite can be downloaded from http://www.pdftron.com/
+//---------------------------------------------------------------------------------------
+
+const fs = require('fs');
+const { PDFNet } = require('../lib/pdfnet.js');
+const PDFTronLicense = require('../LicenseKey/LicenseKey');
+
+((exports) => {
+	'use strict';
+
+	exports.runDataExtractionTest = () => {
+
+		const main = async () => {
+
+			const inputPath = '../TestFiles/';
+			const outputPath = '../TestFiles/Output/';
+
+			//////////////////////////////////////////////////////////////////////////
+
+			await PDFNet.addResourceSearchPath('../lib/');
+
+			//////////////////////////////////////////////////////////////////////////
+			// The following sample illustrates how to extract tables from PDF documents.
+			//////////////////////////////////////////////////////////////////////////
+
+			// Test if the add-on is installed
+			if (!await PDFNet.DataExtractionModule.isModuleAvailable(PDFNet.DataExtractionModule.DataExtractionEngine.e_Tabular)) {
+				console.log('\nUnable to run Data Extraction: PDFTron SDK Tabular Data module not available.');
+				console.log('---------------------------------------------------------------');
+				console.log('The Data Extraction suite is an optional add-on, available for download');
+				console.log('at https://www.pdftron.com/documentation/core/info/modules/. If you have already');
+				console.log('downloaded this module, ensure that the SDK is able to find the required files');
+				console.log('using the PDFNet.addResourceSearchPath() function.\n');
+			}
+			else
+			{
+				try {
+					// Extract tabular data as a JSON file
+					console.log('Extract tabular data as a JSON file');
+
+					let outputFile = outputPath + 'table.json';
+					await PDFNet.DataExtractionModule.extractData(inputPath + 'table.pdf', outputFile, PDFNet.DataExtractionModule.DataExtractionEngine.e_Tabular);
+
+					console.log('Result saved in ' + outputFile);
+
+					///////////////////////////////////////////////////////
+					// Extract tabular data as a JSON string
+					console.log('Extract tabular data as a JSON string');
+
+					outputFile = outputPath + 'financial.json';
+					const json = await PDFNet.DataExtractionModule.extractDataAsString(inputPath + 'financial.pdf', PDFNet.DataExtractionModule.DataExtractionEngine.e_Tabular);
+					fs.writeFileSync(outputFile, json);
+
+					console.log('Result saved in ' + outputFile);
+
+					///////////////////////////////////////////////////////
+					// Extract tabular data as an XLSX file
+					console.log('Extract tabular data as an XLSX file');
+
+					outputFile = outputPath + 'table.xlsx';
+					await PDFNet.DataExtractionModule.extractToXLSX(inputPath + 'table.pdf', outputFile);
+
+					console.log('Result saved in ' + outputFile);
+
+					///////////////////////////////////////////////////////
+					// Extract tabular data as an XLSX stream (also known as filter)
+					console.log('Extract tabular data as an XLSX stream');
+
+					outputFile = outputPath + 'financial.xlsx';
+					const outputXlsxStream = await PDFNet.Filter.createMemoryFilter(0, false);
+					const options = new PDFNet.DataExtractionModule.DataExtractionOptions();
+					options.setPages("1"); // page 1
+					await PDFNet.DataExtractionModule.extractToXLSXWithFilter(inputPath + 'financial.pdf', outputXlsxStream, options);
+					outputXlsxStream.memoryFilterSetAsInputFilter();
+					outputXlsxStream.writeToFile(outputFile, false);
+
+					console.log('Result saved in ' + outputFile);
+				} catch (err) {
+					console.log(err);
+				}
+			}
+
+			//////////////////////////////////////////////////////////////////////////
+			// The following sample illustrates how to extract document structure from PDF documents.
+			//////////////////////////////////////////////////////////////////////////
+
+			// Test if the add-on is installed
+			if (!await PDFNet.DataExtractionModule.isModuleAvailable(PDFNet.DataExtractionModule.DataExtractionEngine.e_DocStructure)) {
+				console.log('\nUnable to run Data Extraction: PDFTron SDK Structured Output module not available.');
+				console.log('---------------------------------------------------------------');
+				console.log('The Data Extraction suite is an optional add-on, available for download');
+				console.log('at https://www.pdftron.com/documentation/core/info/modules/. If you have already');
+				console.log('downloaded this module, ensure that the SDK is able to find the required files');
+				console.log('using the PDFNet.addResourceSearchPath() function.\n');
+			}
+			else
+			{
+				try {
+					// Extract document structure as a JSON file
+					console.log('Extract document structure as a JSON file');
+
+					let outputFile = outputPath + 'paragraphs_and_tables.json';
+					await PDFNet.DataExtractionModule.extractData(inputPath + 'paragraphs_and_tables.pdf', outputFile, PDFNet.DataExtractionModule.DataExtractionEngine.e_DocStructure);
+
+					console.log('Result saved in ' + outputFile);
+
+					///////////////////////////////////////////////////////
+					// Extract document structure as a JSON string
+					console.log('Extract document structure as a JSON string');
+
+					outputFile = outputPath + 'tagged.json';
+					const json = await PDFNet.DataExtractionModule.extractDataAsString(inputPath + 'tagged.pdf', PDFNet.DataExtractionModule.DataExtractionEngine.e_DocStructure);
+					fs.writeFileSync(outputFile, json);
+
+					console.log('Result saved in ' + outputFile);
+				} catch (err) {
+					console.log(err);
+				}
+			}
+
+			//////////////////////////////////////////////////////////////////////////
+			// The following sample illustrates how to extract form fields from PDF documents.
+			//////////////////////////////////////////////////////////////////////////
+
+			// Test if the add-on is installed
+			if (!await PDFNet.DataExtractionModule.isModuleAvailable(PDFNet.DataExtractionModule.DataExtractionEngine.e_Form)) {
+				console.log('\nUnable to run Data Extraction: PDFTron SDK AIFormFieldExtractor module not available.');
+				console.log('---------------------------------------------------------------');
+				console.log('The Data Extraction suite is an optional add-on, available for download');
+				console.log('at https://www.pdftron.com/documentation/core/info/modules/. If you have already');
+				console.log('downloaded this module, ensure that the SDK is able to find the required files');
+				console.log('using the PDFNet.addResourceSearchPath() function.\n');
+			}
+			else
+			{
+				try {
+					// Extract form fields as a JSON file
+					console.log('Extract form fields as a JSON file');
+
+					let outputFile = outputPath + 'formfields-scanned.json';
+					await PDFNet.DataExtractionModule.extractData(inputPath + 'formfields-scanned.pdf', outputFile, PDFNet.DataExtractionModule.DataExtractionEngine.e_Form);
+
+					console.log('Result saved in ' + outputFile);
+
+					///////////////////////////////////////////////////////
+					// Extract form fields as a JSON string
+					console.log('Extract form fields as a JSON string');
+
+					outputFile = outputPath + 'formfields.json';
+					const json = await PDFNet.DataExtractionModule.extractDataAsString(inputPath + 'formfields.pdf', PDFNet.DataExtractionModule.DataExtractionEngine.e_Form);
+					fs.writeFileSync(outputFile, json);
+
+					console.log('Result saved in ' + outputFile);
+				} catch (err) {
+					console.log(err);
+				}
+			}
+
+			//////////////////////////////////////////////////////////////////////////
+
+			console.log('Done.');
+		};
+
+		PDFNet.runWithCleanup(main, PDFTronLicense.Key).catch(function (error) {
+			console.log('Error: ' + JSON.stringify(error));
+		}).then(function () { return PDFNet.shutdown(); });
+	};
+	exports.runDataExtractionTest();
+})(exports);
+// eslint-disable-next-line spaced-comment
+//# sourceURL=DataExtractionTest.js