@pdftron/pdfnet-node-samples 9.4.2 → 9.5.0

package/samples/LogicalStructureTest/LogicalStructureTest.js

@@ -1,5 +1,5 @@
 //---------------------------------------------------------------------------------------
-// Copyright (c) 2001-2022 by PDFTron Systems Inc. All Rights Reserved.
+// Copyright (c) 2001-2023 by PDFTron Systems Inc. All Rights Reserved.
 // Consult legal.txt regarding legal and license information.
 //---------------------------------------------------------------------------------------
 

package/samples/LogicalStructureTest/NODEJS/LogicalStructureTest.js

@@ -0,0 +1,251 @@
+//---------------------------------------------------------------------------------------
+// Copyright (c) 2001-2021 by PDFTron Systems Inc. All Rights Reserved.
+// Consult legal.txt regarding legal and license information.
+//---------------------------------------------------------------------------------------
+
+//---------------------------------------------------------------------------------------
+// This sample explores the structure and content of a tagged PDF document and dumps
+// the structure information to the console window.
+//
+// In tagged PDF documents StructTree acts as a central repository for information
+// related to a PDF document's logical structure. The tree consists of StructElement-s
+// and ContentItem-s which are leaf nodes of the structure tree.
+//
+// The sample can be extended to access and extract the marked-content elements such
+// as text and images.
+//---------------------------------------------------------------------------------------
+
+
+const { PDFNet } = require('../../../lib/pdfnet.js');
+const PDFTronLicense = require('../../LicenseKey/NODEJS/LicenseKey');
+
+((exports) => {
+
+  exports.runLogicalStructureTest = () => {
+
+    const printAndIndent = (printState, indent) => {
+      console.log(printState.str);
+
+      let indentStr = '';
+      for (let i = 0; i < indent; ++i) {
+        indentStr += '  ';
+      }
+    printState.str = indentStr;
+    };
+
+    // Used in code snippet 1.
+    const processStructElement = async(element, indent, printState) => {
+      if (!(await element.isValid())) {
+        return;
+      }
+
+
+      // Print out the type and title info, if any.
+      printAndIndent(printState, indent++);
+      printState.str += 'Type: ' + (await element.getType());
+      if (await element.hasTitle()) {
+        printState.str += '. Title: ' + (await element.getTitle());
+      }
+
+      const num = await element.getNumKids();
+      for (let i = 0; i < num; ++i) {
+        // Check is the kid is a leaf node (i.e. it is a ContentItem).
+        if (await element.isContentItem(i)) {
+          const cont = await element.getAsContentItem(i);
+          const type = await cont.getType();
+
+          const page = await cont.getPage();
+
+          printAndIndent(printState, indent);
+          printState.str += 'Content Item. Part of page #' + (await page.getIndex());
+
+          printAndIndent(printState, indent);
+          switch (type) {
+            case PDFNet.ContentItem.Type.e_MCID:
+            case PDFNet.ContentItem.Type.e_MCR:
+              printState.str += 'MCID: ' + (await cont.getMCID());
+              break;
+            case PDFNet.ContentItem.Type.e_OBJR:
+              {
+                printState.str += 'OBJR ';
+                const refObj = await cont.getRefObj();
+                if (refObj) {
+                  printState.str += '- Referenced Object#: ' + refObj.getObjNum();
+                }
+              }
+              break;
+            default:
+              break;
+          }
+        } else { // the kid is another StructElement node.
+          await processStructElement(await element.getAsStructElem(i), indent, printState);
+        }
+      }
+    };
+
+    // Used in code snippet 2.
+    const processElements = async(reader, printState) => {
+      let element;
+      while (element = await reader.next()) { // Read page contents
+        // In this sample we process only paths & text, but the code can be
+        // extended to handle any element type.
+        const type = await element.getType();
+        if (type === PDFNet.Element.Type.e_path || type === PDFNet.Element.Type.e_text || type === PDFNet.Element.Type.e_path) {
+          switch (type) {
+            case PDFNet.Element.Type.e_path: // Process path ...
+              printState.str += '\nPATH: ';
+              break;
+            case PDFNet.Element.Type.e_text: // Process text ...
+              printState.str += '\nTEXT: ' + (await element.getTextString()) + '\n';
+              break;
+            case PDFNet.Element.Type.e_form: // Process form XObjects
+              printState.str += '\nFORM XObject: ';
+              // reader.formBegin();
+              // await ProcessElements(reader);
+              // reader.end();
+              break;
+          }
+
+          // Check if the element is associated with any structural element.
+          // Content items are leaf nodes of the structure tree.
+          const structParent = await element.getParentStructElement();
+          if (await structParent.isValid()) {
+            // Print out the parent structural element's type, title, and object number.
+            printState.str += ' Type: ' + (await structParent.getType()) + ', MCID: ' + (await element.getStructMCID());
+            if (await structParent.hasTitle()) {
+              printState.str += '. Title: ' + (await structParent.getTitle());
+            }
+            printState.str += ', Obj#: ' + (await (await structParent.getSDFObj()).getObjNum());
+          }
+        }
+      }
+    };
+
+    // Used in code snippet 3.
+    const processElements2 = async(reader, mcidPageMap) => {
+      let element;
+      while (element = await reader.next()) { // Read page contents
+        // In this sample we process only text, but the code can be extended
+        // to handle paths, images, or any other Element type.
+        const mcid = await element.getStructMCID();
+        if (mcid >= 0 && (await element.getType()) === PDFNet.Element.Type.e_text) {
+          const val = await element.getTextString();
+          if (mcid in mcidPageMap) {
+            mcidPageMap[mcid] += val;
+          } else {
+            mcidPageMap[mcid] = val;
+          }
+        }
+      }
+    };
+
+    // Used in code snippet 3.
+    const processStructElement2 = async(element, mcidDocMap, indent, printState) => {
+      if (!(await element.isValid())) {
+        return;
+      }
+
+      // Print out the type and title info, if any.
+      printAndIndent(printState, indent);
+      printState.str += '<' + (await element.getType());
+      if (await element.hasTitle()) {
+        printState.str += ' title="' + (await element.getTitle()) + '"';
+      }
+      printState.str += '>';
+
+      const num = await element.getNumKids();
+      for (let i = 0; i < num; ++i) {
+        if (await element.isContentItem(i)) {
+          const cont = await element.getAsContentItem(i);
+          if ((await cont.getType()) === PDFNet.ContentItem.Type.e_MCID) {
+            const pageNum = await (await cont.getPage()).getIndex();
+            const mcidPageMap = mcidDocMap[pageNum];
+            if (mcidPageMap) {
+              const mcid = await cont.getMCID();
+              if (mcid in mcidPageMap) {
+                printState.str += mcidPageMap[mcid];
+              }
+            }
+          }
+        } else { // the kid is another StructElement node.
+          await processStructElement2(await element.getAsStructElem(i), mcidDocMap, indent + 1, printState);
+        }
+      }
+
+      printAndIndent(printState, indent);
+      printState.str += '</' + (await element.getType()) + '>';
+    };
+
+    const main = async() => {
+      // Relative path to the folder containing test files.
+      const inputPath = '../../TestFiles/';
+      const printState = { str: '' };
+      try { // Extract logical structure from a PDF document
+        const doc = await PDFNet.PDFDoc.createFromFilePath(inputPath + 'tagged.pdf');
+        doc.initSecurityHandler();
+
+        let reader = null;
+        let tree = null;
+
+        console.log('____________________________________________________________');
+        console.log('Sample 1 - Traverse logical structure tree...');
+        tree = await doc.getStructTree();
+        if (await tree.isValid()) {
+          console.log('Document has a StructTree root.');
+          for (let i = 0, numKids = await tree.getNumKids(); i < numKids; ++i) {
+            // Recursively get structure info for all child elements.
+            await processStructElement(await tree.getKid(i), 0, printState);
+          }
+        } else {
+          console.log('This document does not contain any logical structure.');
+        }
+        printAndIndent(printState, 0);
+        console.log('Done 1.');
+
+        console.log('____________________________________________________________');
+        console.log('Sample 2 - Get parent logical structure elements from');
+        console.log('layout elements.');
+        reader = await PDFNet.ElementReader.create();
+        for (let itr = await doc.getPageIterator(); await itr.hasNext(); itr.next()) {
+          reader.beginOnPage(await itr.current());
+          await processElements(reader, printState);
+          reader.end();
+        }
+        printAndIndent(printState, 0);
+        console.log('Done 2.');
+
+        console.log('____________________________________________________________');
+        console.log("Sample 3 - 'XML style' extraction of PDF logical structure and page content.");
+        {
+          const mcidDocMap = {};
+          for (let itr = await doc.getPageIterator(); await itr.hasNext(); itr.next()) {
+            const page = await itr.current();
+            reader.beginOnPage(page);
+            const pageNum = await page.getIndex();
+            const pageMcidMap = {};
+            mcidDocMap[pageNum] = pageMcidMap;
+            await processElements2(reader, pageMcidMap);
+            reader.end();
+          }
+
+          tree = await doc.getStructTree();
+          if (await tree.isValid()) {
+            for (let i = 0, numKids = await tree.getNumKids(); i < numKids; ++i) {
+              await processStructElement2(await tree.getKid(i), mcidDocMap, 0, printState);
+            }
+          }
+        }
+        printAndIndent(printState, 0);
+        console.log('Done 3.');
+        await doc.save(inputPath + 'Output/LogicalStructure.pdf', 0);
+      } catch (err) {
+        console.log(err);
+      }
+    };
+
+    PDFNet.runWithCleanup(main, PDFTronLicense.Key).catch(function(error){console.log('Error: ' + JSON.stringify(error));}).then(function(){return PDFNet.shutdown();});
+  };
+  exports.runLogicalStructureTest();
+})(exports);
+// eslint-disable-next-line spaced-comment
+//# sourceURL=LogicalStructureTest.js

package/samples/LogicalStructureTest/NODEJS/RunTest.sh

@@ -0,0 +1,2 @@
+#!/bin/sh
+node LogicalStructureTest.js

package/samples/OCRTest/NODEJS/OCRTest.js

@@ -0,0 +1,235 @@
+//---------------------------------------------------------------------------------------
+// Copyright (c) 2001-2021 by PDFTron Systems Inc. All Rights Reserved.
+// Consult legal.txt regarding legal and license information.
+//---------------------------------------------------------------------------------------
+
+
+const { PDFNet } = require('../../../lib/pdfnet.js');
+const PDFTronLicense = require('../../LicenseKey/NODEJS/LicenseKey');
+
+((exports) => {
+  'use strict';
+
+  //---------------------------------------------------------------------------------------
+  // The following sample illustrates how to use OCR module
+  //---------------------------------------------------------------------------------------
+  exports.runOCRTest = () => {
+    const main = async () => {
+      try {
+
+        PDFNet.addResourceSearchPath('../../../lib/');
+
+        const useIRIS = await PDFNet.OCRModule.isIRISModuleAvailable();
+        if (!(await PDFNet.OCRModule.isModuleAvailable())) {
+          console.log('\nUnable to run OCRTest: PDFTron SDK OCR module not available.');
+          console.log('---------------------------------------------------------------');
+          console.log('The OCR module is an optional add-on, available for download');
+          console.log('at http://www.pdftron.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.\n');
+
+          return;
+        }
+
+        // Relative path to the folder containing test files.
+        const input_path = '../../TestFiles/OCR/';
+        const output_path = '../../TestFiles/Output/';
+
+        //--------------------------------------------------------------------------------
+        // Example 1) Process image without specifying options, default language - English - is used
+        try {
+
+          // A) Setup empty destination doc
+          const doc = await PDFNet.PDFDoc.create();
+          
+          await doc.initSecurityHandler();
+
+          const opts = new PDFNet.OCRModule.OCROptions();
+          if(useIRIS) opts.setOCREngine('iris');
+
+          // B) Run OCR on the .png with options
+          await PDFNet.OCRModule.imageToPDF(doc, input_path + 'psychomachia_excerpt.png', opts);
+
+          // C) check the result
+          await doc.save(output_path + 'psychomachia_excerpt.pdf', 0);
+
+          console.log('Example 1: psychomachia_excerpt.png');
+
+        } catch (err) {
+          console.log(err);
+        }
+
+        //--------------------------------------------------------------------------------
+        // Example 2) Process document using multiple languages
+        try {
+          // A) Setup empty destination doc
+          const doc = await PDFNet.PDFDoc.create();
+          await doc.initSecurityHandler();
+
+          // B) Setup options with multiple target languages, English will always be considered as secondary language
+          const opts = new PDFNet.OCRModule.OCROptions();
+          if(useIRIS) opts.setOCREngine('iris');
+          opts.addLang('rus');
+          opts.addLang('deu');
+
+          // C) Run OCR on the .jpg with options
+          await PDFNet.OCRModule.imageToPDF(doc, input_path + 'multi_lang.jpg', opts);
+
+          // D) check the result
+          await doc.save(output_path + 'multi_lang.pdf', 0);
+
+          console.log('Example 2: multi_lang.jpg');
+        } catch (err) {
+          console.log(err);
+        }
+
+        //--------------------------------------------------------------------------------
+        // Example 3) Process a .pdf specifying a language - German - and ignore zone comprising a sidebar image 
+        try {
+          // A) Open the .pdf document
+          const doc = await PDFNet.PDFDoc.createFromFilePath(input_path + 'german_kids_song.pdf');
+          doc.initSecurityHandler();
+
+          // B) Setup options with a single language and an ignore zone
+          const opts = new PDFNet.OCRModule.OCROptions();
+          if(useIRIS) opts.setOCREngine('iris');
+          opts.addLang('deu');
+
+          const ignore_zones = [];
+          ignore_zones.push(new PDFNet.Rect(424, 163, 493, 730));
+          opts.addIgnoreZonesForPage(ignore_zones, 1);
+
+          // C) Run OCR on the .pdf with options
+          await PDFNet.OCRModule.processPDF(doc, opts);
+
+          // D) check the result
+          await doc.save(output_path + 'german_kids_song.pdf', 0);
+
+          console.log('Example 3: german_kids_song.pdf');
+        } catch (err) {
+          console.log(err);
+        }
+
+        //--------------------------------------------------------------------------------
+        // Example 4) Process multipage tiff with text/ignore zones specified for each page, optionally provide English as the target language
+        try {
+          // A) Setup empty destination doc
+          const doc = await PDFNet.PDFDoc.create();
+          await doc.initSecurityHandler();
+
+          // B) Setup options with a single language plus text/ignore zones
+          const opts = new PDFNet.OCRModule.OCROptions();
+          if(useIRIS) opts.setOCREngine('iris');
+          opts.addLang('eng');
+
+          var ignore_zones = [];
+          // ignore signature box in the first 2 pages
+          ignore_zones.push(new PDFNet.Rect(1492, 56, 2236, 432));
+          opts.addIgnoreZonesForPage(ignore_zones, 1);
+
+          ignore_zones = [];
+          ignore_zones.push(new PDFNet.Rect(1492, 56, 2236, 432));
+          opts.addIgnoreZonesForPage(ignore_zones, 2);
+
+          // can use a combination of ignore and text boxes to focus on the page area of interest,
+          // as ignore boxes are applied first, we remove the arrows before selecting part of the diagram
+          ignore_zones = [];
+          ignore_zones.push(new PDFNet.Rect(992, 1276, 1368, 1372));
+          opts.addIgnoreZonesForPage(ignore_zones, 3);
+
+
+          const text_zones = [];
+          // we only have text zones selected in page 3
+
+          // select horizontal BUFFER ZONE sign
+          text_zones.push(new PDFNet.Rect(900, 2384, 1236, 2480));
+          // select right vertical BUFFER ZONE sign
+          text_zones.push(new PDFNet.Rect(1960, 1976, 2016, 2296));
+          // select Lot No.
+          text_zones.push(new PDFNet.Rect(696, 1028, 1196, 1128));
+
+          // select part of the plan inside the BUFFER ZONE
+          text_zones.push(new PDFNet.Rect(428, 1484, 1784, 2344));
+          text_zones.push(new PDFNet.Rect(948, 1288, 1672, 1476));
+          opts.addTextZonesForPage(text_zones, 3);
+
+          // C) Run OCR on the .tif with options
+          await PDFNet.OCRModule.imageToPDF(doc, input_path + 'bc_environment_protection.tif', opts);
+
+          // D) check the result
+          await doc.save(output_path + 'bc_environment_protection.pdf', 0);
+
+          console.log('Example 4: bc_environment_protection.tif');
+        } catch (err) {
+          console.log(err);
+        }
+
+        //--------------------------------------------------------------------------------
+        // Example 5) Alternative workflow for extracting OCR result JSON, postprocessing (e.g., removing words not in the dictionary or filtering special
+        // out special characters), and finally applying modified OCR JSON to the source PDF document 
+        try {
+          // A) Open the .pdf document
+          const doc = await PDFNet.PDFDoc.createFromFilePath(input_path + 'zero_value_test_no_text.pdf');
+          await doc.initSecurityHandler();
+
+          const opts = new PDFNet.OCRModule.OCROptions();
+          if(useIRIS) opts.setOCREngine('iris');
+
+          // B) Run OCR on the .pdf with default English language
+          const json = await PDFNet.OCRModule.getOCRJsonFromPDF(doc, opts);
+
+          // C) Post-processing step (whatever it might be)
+          console.log('Have OCR result JSON, re-applying to PDF ');
+
+          // D) Apply potentially modified OCR JSON to the PDF
+          await PDFNet.OCRModule.applyOCRJsonToPDF(doc, json);
+
+          // E) Check the result
+          await doc.save(output_path + 'zero_value_test_no_text.pdf', 0);
+
+          console.log('Example 5: extracting and applying OCR JSON from zero_value_test_no_text.pdf');
+        } catch (err) {
+          console.log(err);
+        }
+
+        //--------------------------------------------------------------------------------
+        // Example 6) The postprocessing workflow has also an option of extracting OCR results in XML format, similar to the one used by TextExtractor
+        try {
+
+          // A) Setup empty destination doc
+          const doc = await PDFNet.PDFDoc.create();
+          await doc.initSecurityHandler();
+
+          const opts = new PDFNet.OCRModule.OCROptions();
+          if(useIRIS) opts.setOCREngine('iris');
+
+          // B) Run OCR on the .tif with default English language, extracting OCR results in XML format. Note that
+          // in the process we convert the source image into PDF. We reuse this PDF document later to add hidden text layer to it.
+          const xml = await PDFNet.OCRModule.getOCRXmlFromImage(doc, input_path + 'physics.tif', opts);
+
+          // C) Post-processing step (whatever it might be)
+          console.log('Have OCR result XML, re-applying to PDF');
+
+          // D) Apply potentially modified OCR XML to the PDF
+          await PDFNet.OCRModule.applyOCRXmlToPDF(doc, xml);
+
+          // E) Check the result
+          await doc.save(output_path + 'physics.pdf', 0);
+
+          console.log('Example 6: extracting and applying OCR XML from physics.tif');
+        } catch (err) {
+          console.log(err);
+        }
+        console.log('Done.');
+      } catch (err) {
+        console.log(err);
+      }
+    };
+    PDFNet.runWithCleanup(main, PDFTronLicense.Key).catch(function(error) {
+      console.log('Error: ' + JSON.stringify(error));
+    }).then(function(){ return PDFNet.shutdown(); });
+  };
+  exports.runOCRTest();
+})(exports);
+// eslint-disable-next-line spaced-comment
+//# sourceURL=OCRTest.js

package/samples/OCRTest/NODEJS/RunTest.sh

@@ -0,0 +1,2 @@
+#!/bin/sh
+node OCRTest.js