@pdftron/pdfnet-node-samples 9.5.0-5 → 9.5.0-5-beta

package/{samples/DataExtractionTest → DataExtractionTest}/DataExtractionTest.js

@@ -1,5 +1,5 @@
 //---------------------------------------------------------------------------------------
-// Copyright (c) 2001-2023 by PDFTron Systems Inc. All Rights Reserved.
+// Copyright (c) 2001-2025 by Apryse Software Inc. All Rights Reserved.
 // Consult legal.txt regarding legal and license information.
 //---------------------------------------------------------------------------------------
 
@@ -7,7 +7,7 @@
 // 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/
+// The Apryse SDK Data Extraction suite can be downloaded from http://www.apryse.com/
 //---------------------------------------------------------------------------------------
 
 const fs = require('fs');
@@ -26,7 +26,7 @@ const PDFTronLicense = require('../LicenseKey/LicenseKey');
 
 			//////////////////////////////////////////////////////////////////////////
 
-			await PDFNet.addResourceSearchPath('../lib/');
+			await PDFNet.addResourceSearchPath('../../lib/');
 
 			//////////////////////////////////////////////////////////////////////////
 			// The following sample illustrates how to extract tables from PDF documents.
@@ -34,10 +34,10 @@ const PDFTronLicense = require('../LicenseKey/LicenseKey');
 
 			// 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('\nUnable to run Data Extraction: Apryse 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('at https://docs.apryse.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');
 			}
@@ -78,7 +78,7 @@ const PDFTronLicense = require('../LicenseKey/LicenseKey');
 					outputFile = outputPath + 'financial.xlsx';
 					const outputXlsxStream = await PDFNet.Filter.createMemoryFilter(0, false);
 					const options = new PDFNet.DataExtractionModule.DataExtractionOptions();
-					options.setPages("1"); // page 1
+					options.setPages('1'); // page 1
 					await PDFNet.DataExtractionModule.extractToXLSXWithFilter(inputPath + 'financial.pdf', outputXlsxStream, options);
 					outputXlsxStream.memoryFilterSetAsInputFilter();
 					outputXlsxStream.writeToFile(outputFile, false);
@@ -95,10 +95,10 @@ const PDFTronLicense = require('../LicenseKey/LicenseKey');
 
 			// 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('\nUnable to run Data Extraction: Apryse 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('at https://docs.apryse.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');
 			}
@@ -133,10 +133,10 @@ const PDFTronLicense = require('../LicenseKey/LicenseKey');
 
 			// 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('\nUnable to run Data Extraction: Apryse 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('at https://docs.apryse.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');
 			}
@@ -160,6 +160,137 @@ const PDFTronLicense = require('../LicenseKey/LicenseKey');
 					fs.writeFileSync(outputFile, json);
 
 					console.log('Result saved in ' + outputFile);
+
+					//////////////////////////////////////////////////////////////////////////
+					// Detect and add form fields to a PDF document.
+					// Document already has form fields, and this sample will update to new found fields.
+					{
+						console.log('Detect and add form fields in a PDF file, keep new fields');
+
+						const doc = await PDFNet.PDFDoc.createFromFilePath(inputPath + 'formfields-scanned-withfields.pdf');
+
+						await PDFNet.DataExtractionModule.detectAndAddFormFieldsToPDF(doc);
+						outputFile = outputPath + 'formfields-scanned-fields-new.pdf';
+						await doc.save(outputFile, PDFNet.SDFDoc.SaveOptions.e_linearized);
+
+						console.log('Result saved in ' + outputFile);
+					}
+
+					//////////////////////////////////////////////////////////////////////////
+					// Detect and add form fields to a PDF document.
+					// Document already has form fields, and this sample will keep the original fields.
+					{
+						console.log('Detect and add form fields in a PDF file, keep old fields');
+
+						const doc = await PDFNet.PDFDoc.createFromFilePath(inputPath + 'formfields-scanned-withfields.pdf');
+
+						const options = new PDFNet.DataExtractionModule.DataExtractionOptions();
+						options.setOverlappingFormFieldBehavior('KeepOld');
+
+						await PDFNet.DataExtractionModule.detectAndAddFormFieldsToPDF(doc, options);
+						outputFile = outputPath + 'formfields-scanned-fields-old.pdf';
+						await doc.save(outputFile, PDFNet.SDFDoc.SaveOptions.e_linearized);
+					}
+
+					console.log('Result saved in ' + outputFile);
+
+				} catch (err) {
+					console.log(err);
+				}
+			}
+
+			//////////////////////////////////////////////////////////////////////////
+			// The following sample illustrates how to extract key-value pairs from PDF documents.
+			//////////////////////////////////////////////////////////////////////////
+			if (!await PDFNet.DataExtractionModule.isModuleAvailable(PDFNet.DataExtractionModule.DataExtractionEngine.e_GenericKeyValue)) {
+				console.log();
+				console.log('Unable to run Data Extraction: Apryse SDK AIPageObjectExtractor module not available.');
+				console.log('---------------------------------------------------------------');
+				console.log('The Data Extraction suite is an optional add-on, available for download');
+				console.log('at http://www.apryse.com/. If you have already downloaded this');
+				console.log('module, ensure that the SDK is able to find the required files');
+				console.log('using the PDFNet.addResourceSearchPath() function.');
+				console.log();
+			}
+			else
+			{
+				try {
+					// Simple example: Extract Keys & Values as a JSON file
+					console.log('Extract Key-Value pairs as a JSON file');
+					await PDFNet.DataExtractionModule.extractData(inputPath + 'newsletter.pdf', outputPath + 'newsletter_key_val.json', PDFNet.DataExtractionModule.DataExtractionEngine.e_GenericKeyValue);
+					console.log('Result saved in ' + outputPath + 'newsletter_key_val.json');
+					
+					const options = new PDFNet.DataExtractionModule.DataExtractionOptions();
+					options.setPages('2-4');
+				
+					const p2ExclusionZones = [];
+					// Exclude the ad on page 2
+					// These coordinates are in PDF user space, with the origin at the bottom left corner of the page
+					// Coordinates rotate with the page, if it has rotation applied.
+					p2ExclusionZones.push(new PDFNet.Rect(166, 47, 562, 222));
+					options.addExclusionZonesForPage(p2ExclusionZones, 2);
+				
+					const p4InclusionZones = [];
+					const p4ExclusionZones = [];
+					// Only include the article text for page 4, exclude ads and headings
+					p4InclusionZones.push(new PDFNet.Rect(30, 432, 562, 684));
+					p4ExclusionZones.push(new PDFNet.Rect(30, 657, 295, 684));
+					options.addInclusionZonesForPage(p4InclusionZones, 4);
+					options.addExclusionZonesForPage(p4ExclusionZones, 4);
+					console.log('Extract Key-Value pairs from specific pages and zones as a JSON file');
+					await PDFNet.DataExtractionModule.extractData(inputPath + 'newsletter.pdf', outputPath + 'newsletter_key_val_with_zones.json', PDFNet.DataExtractionModule.DataExtractionEngine.e_GenericKeyValue, options);
+					console.log('Result saved in ' + outputPath + 'newsletter_key_val_with_zones.json');
+				} catch (err) {
+					console.log(err);
+				}
+			}
+
+			//////////////////////////////////////////////////////////////////////////
+			// The following sample illustrates how to extract document classes from PDF documents.
+			//////////////////////////////////////////////////////////////////////////
+
+			// Test if the add-on is installed
+			if (!await PDFNet.DataExtractionModule.isModuleAvailable(PDFNet.DataExtractionModule.DataExtractionEngine.e_DocClassification)) {
+				console.log('\nUnable to run Data Extraction: Apryse SDK AIPageObjectExtractor module not available.');
+				console.log('---------------------------------------------------------------');
+				console.log('The Data Extraction suite is an optional add-on, available for download');
+				console.log('at https://docs.apryse.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 {
+					// Simple example: classify pages as a JSON file
+					console.log('Classify pages as a JSON file');
+
+					let outputFile = outputPath + 'Invoice_Classified.json';
+					await PDFNet.DataExtractionModule.extractData(inputPath + 'Invoice.pdf', outputFile, PDFNet.DataExtractionModule.DataExtractionEngine.e_DocClassification);
+
+					console.log('Result saved in ' + outputFile);
+
+					///////////////////////////////////////////////////////
+					// Classify pages as a JSON string
+					console.log('Classify pages as a JSON string');
+
+					outputFile = outputPath + 'Scientific_Publication_Classified.json';
+					const json = await PDFNet.DataExtractionModule.extractDataAsString(inputPath + 'Scientific_Publication.pdf', PDFNet.DataExtractionModule.DataExtractionEngine.e_DocClassification);
+					fs.writeFileSync(outputFile, json);
+
+					console.log('Result saved in ' + outputFile);
+					
+					///////////////////////////////////////////////////////
+					// Example with customized options:
+					console.log('Classify pages with customized options');
+
+					const options = new PDFNet.DataExtractionModule.DataExtractionOptions();
+					// Classes that don't meet the minimum confidence threshold of 70% will not be listed in the output JSON
+					options.setMinimumConfidenceThreshold(0.7);
+					outputFile = outputPath + 'Email_Classified.json';
+					await PDFNet.DataExtractionModule.extractData(inputPath + 'Email.pdf', outputFile, PDFNet.DataExtractionModule.DataExtractionEngine.e_DocClassification, options);
+
+					console.log('Result saved in ' + outputFile);
+					
 				} catch (err) {
 					console.log(err);
 				}

package/{samples/DigitalSignaturesTest → DigitalSignaturesTest}/DigitalSignaturesTest.js

@@ -1,5 +1,5 @@
 //---------------------------------------------------------------------------------------
-// Copyright (c) 2001-2023 by PDFTron Systems Inc. All Rights Reserved.
+// Copyright (c) 2001-2025 by Apryse Software Inc. All Rights Reserved.
 // Consult legal.txt regarding legal and license information.
 //---------------------------------------------------------------------------------------
 
@@ -356,11 +356,85 @@ const PDFTronLicense = require('../LicenseKey/LicenseKey');
       console.log('================================================================================');
     }
 
-    const TimestampAndEnableLTV = async (in_docpath, in_trusted_cert_path, in_appearance_img_path, in_outpath) => {
+    const CustomSigningAPI = async (doc_path, cert_field_name, private_key_file_path, keyfile_password, public_key_file_path, appearance_image_path, digest_algorithm_type, PAdES_signing_mode, output_path) => {
+      console.log('================================================================================');
+      console.log('Custom signing PDF document');
+
+      const doc = await PDFNet.PDFDoc.createFromFilePath(doc_path);
+      doc.initSecurityHandler();
+
+      const page1 = await doc.getPage(1);
+
+      const digsig_field = await doc.createDigitalSignatureField(cert_field_name);
+      const widgetAnnot = await PDFNet.SignatureWidget.createWithDigitalSignatureField(doc, new PDFNet.Rect(143, 287, 219, 306), digsig_field);
+      await page1.annotPushBack(widgetAnnot);
+
+      // (OPTIONAL) Add an appearance to the signature field.
+      const img = await PDFNet.Image.createFromFile(doc, appearance_image_path);
+      await widgetAnnot.createSignatureAppearance(img);
+
+      // Create a digital signature dictionary inside the digital signature field, in preparation for signing.
+      await digsig_field.createSigDictForCustomSigning('Adobe.PPKLite',
+        PAdES_signing_mode ? PDFNet.DigitalSignatureField.SubFilterType.e_ETSI_CAdES_detached : PDFNet.DigitalSignatureField.SubFilterType.e_adbe_pkcs7_detached,
+        7500); // For security reasons, set the contents size to a value greater than but as close as possible to the size you expect your final signature to be, in bytes.
+             // ... or, if you want to apply a certification signature, use CreateSigDictForCustomCertification instead.
+
+      // (OPTIONAL) Set the signing time in the signature dictionary, if no secure embedded timestamping support is available from your signing provider.
+      const current_date = new PDFNet.Date();
+      await current_date.setCurrentTime();
+      await digsig_field.setSigDictTimeOfSigning(current_date);
+
+      await doc.save(output_path, PDFNet.SDFDoc.SaveOptions.e_incremental);
+
+      // Digest the relevant bytes of the document in accordance with ByteRanges surrounding the signature.
+      const pdf_digest = await digsig_field.calculateDigest(digest_algorithm_type);
+
+      const signer_cert = await PDFNet.X509Certificate.createFromFile(public_key_file_path);
+
+      // Optionally, you can add a custom signed attribute at this point, such as one of the PAdES ESS attributes.
+      // The function we provide takes care of generating the correct PAdES ESS attribute depending on your digest algorithm.
+      const pades_versioned_ess_signing_cert_attribute = await PDFNet.DigitalSignatureField.generateESSSigningCertPAdESAttribute(signer_cert, digest_algorithm_type);
+
+      // Generate the signedAttrs component of CMS, passing any optional custom signedAttrs (e.g. PAdES ESS).
+      // The signedAttrs are certain attributes that become protected by their inclusion in the signature.
+      const signedAttrs = await PDFNet.DigitalSignatureField.generateCMSSignedAttributes(pdf_digest, pades_versioned_ess_signing_cert_attribute);
+
+      // Calculate the digest of the signedAttrs (i.e. not the PDF digest, this time).
+      const signedAttrs_digest = await PDFNet.DigestAlgorithm.calculateDigest(digest_algorithm_type, signedAttrs);
+
+      //////////////////////////// custom digest signing starts ////////////////////////////
+      // At this point, you can sign the digest (for example, with HSM). We use our own SignDigest function instead here as an example,
+      // which you can also use for your purposes if necessary as an alternative to the handler/callback APIs (i.e. Certify/SignOnNextSave).
+      const signature_value = await PDFNet.DigestAlgorithm.signDigest(
+        signedAttrs_digest,
+        digest_algorithm_type,
+        private_key_file_path,
+        keyfile_password);
+      //////////////////////////// custom digest signing ends //////////////////////////////
+
+      // Then, load all your chain certificates into a container of X509Certificate.
+      const chain_certs = [];
+
+      // Then, create ObjectIdentifiers for the algorithms you have used.
+      // Here we use digest_algorithm_type (usually SHA256) for hashing, and RSAES-PKCS1-v1_5 (specified in the private key) for signing.
+      const digest_algorithm_oid = await PDFNet.ObjectIdentifier.createFromDigestAlgorithm(digest_algorithm_type);
+      const signature_algorithm_oid = await PDFNet.ObjectIdentifier.createFromPredefined(PDFNet.ObjectIdentifier.Predefined.e_RSA_encryption_PKCS1);
+
+      // Then, put the CMS signature components together.
+      const cms_signature = await PDFNet.DigitalSignatureField.generateCMSSignature(
+        signer_cert, chain_certs, digest_algorithm_oid, signature_algorithm_oid, signature_value, signedAttrs);
+
+      // Write the signature to the document.
+      await doc.saveCustomSignature(cms_signature, digsig_field, output_path);
+
+      console.log('================================================================================');
+    };
+
+    const TimestampAndEnableLTV = async (in_docpath, in_tsa_url, in_trusted_cert_path, in_appearance_img_path, in_outpath) => {
       const doc = await PDFNet.PDFDoc.createFromFilePath(in_docpath);
       doc.initSecurityHandler();
       const doctimestamp_signature_field = await doc.createDigitalSignatureField();
-      const tst_config = await PDFNet.TimestampingConfiguration.createFromURL('http://rfc3161timestamp.globalsign.com/advanced');
+      const tst_config = await PDFNet.TimestampingConfiguration.createFromURL(in_tsa_url);
       const opts = await PDFNet.VerificationOptions.create(PDFNet.VerificationOptions.SecurityLevel.e_compatibility_and_archiving);
       /* It is necessary to add to the VerificationOptions a trusted root certificate corresponding to 
       the chain used by the timestamp authority to sign the timestamp token, in order for the timestamp
@@ -439,9 +513,9 @@ const PDFTronLicense = require('../LicenseKey/LicenseKey');
       try {
         await CertifyPDF(input_path + 'waiver_withApprovalField.pdf',
         'PDFTronCertificationSig',
-        input_path + 'pdftron.pfx',
+        input_path + 'apryse.pfx',
         'password',
-        input_path + 'pdftron.bmp',
+        input_path + 'apryse.bmp',
         output_path + 'waiver_withApprovalField_certified_output.pdf');
         await PrintSignaturesInfo(output_path + 'waiver_withApprovalField_certified_output.pdf');
       } catch (err) {
@@ -453,7 +527,7 @@ const PDFTronLicense = require('../LicenseKey/LicenseKey');
       try {
         await SignPDF(input_path + 'waiver_withApprovalField_certified.pdf',
         'PDFTronApprovalSig',
-        input_path + 'pdftron.pfx',
+        input_path + 'apryse.pfx',
         'password',
         input_path + 'signature.jpg',
         output_path + 'waiver_withApprovalField_certified_approved_output.pdf');
@@ -475,9 +549,9 @@ const PDFTronLicense = require('../LicenseKey/LicenseKey');
       }
 
       //////////////////// TEST 4: Verify a document's digital signatures.
-      // EXPERIMENTAL. Digital signature verification is undergoing active development, but currently does not support a number of features. If we are missing a feature that is important to you, or if you have files that do not act as expected, please contact us using one of the following forms: https://www.pdftron.com/form/trial-support/ or https://www.pdftron.com/form/request/
+      // EXPERIMENTAL. Digital signature verification is undergoing active development, but currently does not support a number of features. If we are missing a feature that is important to you, or if you have files that do not act as expected, please contact us using one of the following forms: https://apryse.com/form/trial-support or https://apryse.com/form/request
       try {
-        if (!(await VerifyAllAndPrint(input_path + 'waiver_withApprovalField_certified_approved.pdf', input_path + 'pdftron.cer'))) {
+        if (!(await VerifyAllAndPrint(input_path + 'waiver_withApprovalField_certified_approved.pdf', input_path + 'apryse.cer'))) {
           ret = 1;
         }
       } catch (err) {
@@ -487,7 +561,7 @@ const PDFTronLicense = require('../LicenseKey/LicenseKey');
 
       //////////////////// TEST 5: Verify a document's digital signatures in a simple fashion using the document API.
       try {
-        if (!(await VerifySimple(input_path + 'waiver_withApprovalField_certified_approved.pdf', input_path + 'pdftron.cer'))) {
+        if (!(await VerifySimple(input_path + 'waiver_withApprovalField_certified_approved.pdf', input_path + 'apryse.cer'))) {
           ret = 1;
         }
       } catch (err) {
@@ -495,10 +569,50 @@ const PDFTronLicense = require('../LicenseKey/LicenseKey');
         ret = 1;
       }
 
-      //////////////////// TEST 6: Timestamp a document, then add Long Term Validation (LTV) information for the DocTimeStamp.
+      //////////////////// TEST 6: Custom signing API.
+      // The Apryse custom signing API is a set of APIs related to cryptographic digital signatures
+      // which allows users to customize the process of signing documents. Among other things, this
+      // includes the capability to allow for easy integration of PDF-specific signing-related operations
+      // with access to Hardware Security Module (HSM) tokens/devices, access to cloud keystores, access
+      // to system keystores, etc.
+      try {
+        await CustomSigningAPI(input_path + 'waiver.pdf',
+          'PDFTronCertificationSig',
+          input_path + 'apryse.pfx',
+          'password',
+          input_path + 'apryse.cer',
+          input_path + 'signature.jpg',
+          PDFNet.DigestAlgorithm.Type.e_SHA256,
+          true,
+          output_path + 'waiver_custom_signed.pdf');
+      } catch (err) {
+        console.log(err);
+        ret = 1;
+      }
+
+      //////////////////// TEST 7: Timestamp a document, then add Long Term Validation (LTV) information for the DocTimeStamp.
       // try {
+      //   // Replace YOUR_URL_OF_TSA with the timestamp authority (TSA) URL to use during timestamping.
+      //   // For example, as of June 2025, http://timestamp.globalsign.com/tsa/r6advanced1 was usable.
+      //   // Note that this url may not work in the future. A reliable solution requires using your own TSA.
+      //   const tsa_url = 'YOUR_URL_OF_TSA';
+      //   if (tsa_url == 'YOUR_URL_OF_TSA')
+      //   {
+      //     throw new Error('The URL of your timestamp authority was not specified.');
+      //   }
+      //
+      //   // Replace YOUR_CERTIFICATE with the trusted root certificate corresponding to the chain used by the timestamp authority.
+      //   // For example, as of June 2025, https://secure.globalsign.net/cacert/root-r6.crt was usable.
+      //   // Note that this certificate may not work in the future. A reliable solution requires using your own TSA certificate.
+      //   const trusted_cert_path = 'YOUR_CERTIFICATE';
+      //   if (trusted_cert_path == 'YOUR_CERTIFICATE')
+      //   {
+      //     throw new Error('The path to your timestamp authority trusted root certificate was not specified.');
+      //   }
+      //
       //   if (!(await TimestampAndEnableLTV(input_path + 'waiver.pdf',
-      //   input_path + 'GlobalSignRootForTST.cer',
+      //   tsa_url,
+      //   trusted_cert_path,
       //   input_path + 'signature.jpg',
       //   output_path + 'waiver_DocTimeStamp_LTV.pdf'))) {
       //     ret = 1;
@@ -524,4 +638,4 @@ const PDFTronLicense = require('../LicenseKey/LicenseKey');
   exports.runDigitalSignatureTest();
 })(exports);
 // eslint-disable-next-line spaced-comment
-//# sourceURL=DigitalSignatureTest.js
+//# sourceURL=DigitalSignatureTest.js