@pdftron/pdfnet-node-samples 9.4.2 → 9.5.0

package/samples/TextExtractTest/NODEJS/TextExtractTest.js

@@ -0,0 +1,287 @@
+//---------------------------------------------------------------------------------------
+// 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) => {
+
+  exports.runTextExtractTest = async () => {
+    // A utility method used to dump all text content in the console window.
+    const dumpAllText = async (reader) => {
+      let element;
+      let bbox;
+      let arr;
+      while ((element = await reader.next()) !== null) {
+        switch (await element.getType()) {
+          case PDFNet.Element.Type.e_text_begin:
+            console.log('\n--> Text Block Begin');
+            break;
+          case PDFNet.Element.Type.e_text_end:
+            console.log('\n--> Text Block End');
+            break;
+          case PDFNet.Element.Type.e_text:
+            bbox = await element.getBBox();
+            console.log('\n--> BBox: ' + bbox.x1.toFixed(2) + ', ' + bbox.y1.toFixed(2) + ', ' + bbox.x2.toFixed(2) + ', ' + bbox.y2.toFixed(2) + '\n');
+            arr = await element.getTextString();
+            console.log(arr);
+            break;
+          case PDFNet.Element.Type.e_text_new_line:
+            console.log('\n--> New Line');
+            break;
+          case PDFNet.Element.Type.e_form:
+            reader.formBegin();
+            await dumpAllText(reader);
+            reader.end();
+            break;
+        }
+      }
+    };
+
+    // helper method for ReadTextFromRect
+    const rectTextSearch = async (reader, pos, srchStr) => {
+      let element;
+      let arr;
+      while ((element = await reader.next()) !== null) {
+        let bbox;
+        switch (await element.getType()) {
+          case PDFNet.Element.Type.e_text:
+            bbox = await element.getBBox();
+            if (await bbox.intersectRect(bbox, pos)) {
+              arr = await element.getTextString();
+              srchStr += arr + '\n';
+            }
+            break;
+          case PDFNet.Element.Type.e_text_new_line:
+            break;
+          case PDFNet.Element.Type.e_form:
+            reader.formBegin();
+            srchStr += await rectTextSearch(reader, pos, srchStr); // possibly need srchStr = ...
+            reader.end();
+            break;
+        }
+      }
+      return srchStr;
+    };
+
+    const readTextFromRect = async (page, pos, reader) => {
+      let srchStr = '';
+      reader.beginOnPage(page); // uses default parameters.
+      srchStr += await rectTextSearch(reader, pos, srchStr);
+      reader.end();
+      return srchStr;
+    };
+
+    const twoDigitHex = function (num) {
+      const hexStr = num.toString(16).toUpperCase();
+      return ('0' + hexStr).substr(-2);
+    }
+
+    const printStyle = async (s) => {
+      const rgb = await s.getColor();
+      const rColorVal = await rgb.get(0);
+      const gColorVal = await rgb.get(1);
+      const bColorVal = await rgb.get(2);
+      const rgbHex = twoDigitHex(rColorVal) + twoDigitHex(gColorVal) + twoDigitHex(bColorVal)
+      const fontName = await s.getFontName();
+      const fontSize = await s.getFontSize();
+      const serifOutput = ((await s.isSerif()) ? ' sans-serif; ' : ' ');
+      const returnString = ' style="font-family:' + fontName + '; font-size:' + fontSize + ';' + serifOutput + 'color:#' + rgbHex + ';"';
+      return returnString;
+    };
+
+    const main = async () => {
+      // eslint-disable-next-line no-unused-vars
+      let ret = 0;
+
+      // Relative path to the folder containing test files.
+      const inputPath = '../../TestFiles/';
+      const inputFilename = 'newsletter.pdf'; // addimage.pdf, newsletter.pdf
+
+      const example1Basic = false;
+      const example2XML = false;
+      const example3Wordlist = false;
+      const example4Advanced = true;
+      const example5LowLevel = false;
+
+      try {
+        await PDFNet.startDeallocateStack();
+        const doc = await PDFNet.PDFDoc.createFromFilePath(inputPath + inputFilename);
+        doc.initSecurityHandler();
+
+        const page = await doc.getPage(1);
+
+        if (page.id === '0') {
+          console.log('Page not found.');
+          return 1;
+        }
+
+        const txt = await PDFNet.TextExtractor.create();
+        txt.begin(page);
+
+        let text;
+        let line;
+        let word;
+
+        // Example 1. Get all text on the page in a single string.
+        // Words will be separated with space or new line characters.
+        if (example1Basic) {
+          const wordCount = await txt.getWordCount();
+          console.log('Word Count: ' + wordCount);
+          text = await txt.getAsText();
+          console.log('\n\n- GetAsText --------------------------');
+          console.log(text);
+          console.log('-----------------------------------------------------------');
+        }
+
+        // Example 2. Get XML logical structure for the page.
+        if (example2XML) {
+          text = await txt.getAsXML(PDFNet.TextExtractor.XMLOutputFlags.e_words_as_elements | PDFNet.TextExtractor.XMLOutputFlags.e_output_bbox | PDFNet.TextExtractor.XMLOutputFlags.e_output_style_info);
+          console.log('\n\n- GetAsXML  --------------------------\n' + text);
+          console.log('-----------------------------------------------------------');
+        }
+
+        // Example 3. Extract words one by one.
+        if (example3Wordlist) {
+          line = await txt.getFirstLine();
+          for (; (await line.isValid()); line = (await line.getNextLine())) {
+            for (word = await line.getFirstWord(); await word.isValid(); word = await word.getNextWord()) {
+              text = await word.getString();
+              console.log(text);
+            }
+          }
+          console.log('-----------------------------------------------------------');
+        }
+
+        // Example 4. A more advanced text extraction example. 
+        // The output is XML structure containing paragraphs, lines, words, 
+        // as well as style and positioning information.
+        if (example4Advanced) {
+          let b;
+          let q;
+          let curFlowID = -1;
+          let curParaID = -1;
+
+          console.log('<PDFText>');
+
+          // For each line on the page...
+          for (line = await txt.getFirstLine(); await line.isValid(); line = await line.getNextLine()) {
+            if ((await line.getNumWords()) === 0) {
+              continue;
+            }
+            if (curFlowID !== await line.getFlowID()) {
+              if (curFlowID !== -1) {
+                if (curParaID !== -1) {
+                  curParaID = -1;
+                  console.log('</Para>');
+                }
+                console.log('</Flow>');
+              }
+              curFlowID = await line.getFlowID();
+              console.log('<Flow id="' + curFlowID + '">');
+            }
+            if (curParaID !== await line.getParagraphID()) {
+              if (curParaID !== -1) {
+                console.log('</Para>');
+              }
+              curParaID = await line.getParagraphID();
+              console.log('<Para id="' + curParaID + '">');
+            }
+            b = await line.getBBox();
+            const lineStyle = await line.getStyle();
+            let outputStringLineBox = '<Line box="' + b.x1.toFixed(2) + ', ' + b.y1.toFixed(2) + ', ' + b.x2.toFixed(2) + ', ' + b.y2.toFixed(2) + '"';
+            outputStringLineBox += (await printStyle(lineStyle));
+            const currentLineNum = await line.getCurrentNum();
+            outputStringLineBox += ' cur_num="' + currentLineNum + '">';
+            console.log(outputStringLineBox);
+
+            // For each word in the line...
+            for (word = await line.getFirstWord(); await word.isValid(); word = await word.getNextWord()) {
+              // output bounding box for the word
+              q = await word.getBBox();
+              const currentNum = await word.getCurrentNum();
+              let outputStringWord = '<Word box="' + q.x1.toFixed(2) + ', ' + q.y1.toFixed(2) + ', ' + q.x2.toFixed(2) + ', ' + q.y2.toFixed(2) + '" cur_num="' + currentNum + '"';
+              const sz = await word.getStringLen();
+              if (sz === 0) {
+                continue;
+              }
+              // if the word style is different from the parent style, output the new style
+              const sty = await word.getStyle();
+              if (!(await sty.compare(lineStyle))) {
+                outputStringWord += await printStyle(sty);
+              }
+              outputStringWord += '>' + (await word.getString()) + '</Word>';
+              console.log(outputStringWord);
+            }
+            console.log('</Line>');
+          }
+          if (curFlowID !== -1) {
+            if (curParaID !== -1) {
+              curParaID = -1;
+              console.log('</Para>');
+            }
+            console.log('</Flow>');
+          }
+          console.log('</PDFText>');
+        }
+        await PDFNet.endDeallocateStack();
+      } catch (err) {
+        console.log(err);
+        console.log(err.stack);
+        ret = 1;
+      }
+
+
+      if (example5LowLevel) {
+        ret = 0;
+        try {
+          await PDFNet.startDeallocateStack();
+          const doc = await PDFNet.PDFDoc.createFromFilePath(inputPath + inputFilename);
+          doc.initSecurityHandler();
+
+          // Example 1. Extract all text content from the document
+          const reader = await PDFNet.ElementReader.create();
+          const itr = await doc.getPageIterator(1);
+
+          //  Read every page
+          for (itr; await itr.hasNext(); itr.next()) {
+            const page = await itr.current();
+            reader.beginOnPage(page);
+            await dumpAllText(reader);
+            reader.end();
+          }
+          // Example 2. Extract text content based on the
+          // selection rectangle.
+          console.log('\n----------------------------------------------------');
+          console.log('Extract text based on the selection rectangle.');
+          console.log('----------------------------------------------------');
+
+
+          const firstPage = await (await doc.getPageIterator()).current();
+          let s1 = await readTextFromRect(firstPage, (await PDFNet.Rect.init(27, 392, 563, 534)), reader);
+          console.log('\nField 1: ' + s1);
+
+          s1 = await readTextFromRect(firstPage, (await PDFNet.Rect.init(28, 551, 106, 623)), reader);
+          console.log('Field 2: ' + s1);
+
+          s1 = await readTextFromRect(firstPage, (await PDFNet.Rect.init(208, 550, 387, 621)), reader);
+          console.log('Field 3: ' + s1);
+
+          // ...
+          console.log('Done');
+          await PDFNet.endDeallocateStack();
+        } catch (err) {
+          console.log(err.stack);
+          ret = 1;
+        }
+      }
+    };
+    PDFNet.runWithCleanup(main, PDFTronLicense.Key).catch(function (error) { console.log('Error: ' + JSON.stringify(error)); }).then(function () { return PDFNet.shutdown(); });
+  };
+  exports.runTextExtractTest();
+})(exports);
+// eslint-disable-next-line spaced-comment
+//# sourceURL=TextExtractTest.js

package/samples/TextExtractTest/TextExtractTest.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/TextSearchTest/NODEJS/RunTest.sh

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

package/samples/TextSearchTest/NODEJS/TextSearchTest.js

@@ -0,0 +1,122 @@
+//---------------------------------------------------------------------------------------
+// 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) => {
+
+  exports.runTextSearchTest = () => {
+
+    const main = async() => {
+      // Relative path to the folder containing test files.
+      const inputURL = '../../TestFiles/';
+      const inputFilename = 'credit card numbers.pdf'; // addimage.pdf, newsletter.pdf
+
+      try {
+        const doc = await PDFNet.PDFDoc.createFromFilePath(inputURL + inputFilename);
+        doc.initSecurityHandler();
+
+        const txtSearch = await PDFNet.TextSearch.create();
+        let mode = PDFNet.TextSearch.Mode.e_whole_word + PDFNet.TextSearch.Mode.e_page_stop; // Uses both whole word and page stop
+        let pattern = 'joHn sMiTh';
+
+        txtSearch.begin(doc, pattern, mode); // searches for the "pattern" in the document while following the inputted modes.
+
+        let step = 0;
+
+        // call Run() iteratively to find all matching instances of the word 'joHn sMiTh'
+        /* eslint-disable-next-line no-constant-condition */
+        while (true) {
+          const result = await txtSearch.run();
+          let hlts;
+          if (result.code === PDFNet.TextSearch.ResultCode.e_found) {
+            if (step === 0) { // Step 0: found "John Smith"
+              // note that, here, 'ambient_str' and 'highlights' are not written to,
+              // as 'e_ambient_string' and 'e_highlight' are not set.
+              console.log(result.out_str + "'s credit card number is: ");
+
+              // now switch to using regular expressions to find John's credit card number
+              mode = await txtSearch.getMode();
+              mode += PDFNet.TextSearch.Mode.e_reg_expression + PDFNet.TextSearch.Mode.e_highlight;
+              txtSearch.setMode(mode);
+              pattern = '\\d{4}-\\d{4}-\\d{4}-\\d{4}'; // or "(\\d{4}-){3}\\d{4}"
+              txtSearch.setPattern(pattern);
+
+              ++step;
+            } else if (step === 1) {
+              // step 1: found John's credit card number
+              console.log('  ' + result.out_str);
+              // note that, here, 'hlts' is written to, as 'e_highlight' has been set.
+              // output the highlight info of the credit card number.
+              hlts = result.highlights;
+              hlts.begin(doc);
+              while ((await hlts.hasNext())) {
+                const highlightPageNum = await hlts.getCurrentPageNumber();
+                console.log('The current highlight is from page: ' + highlightPageNum);
+                await hlts.next();
+              }
+              // see if there is an AMEX card number
+              pattern = '\\d{4}-\\d{6}-\\d{5}';
+              txtSearch.setPattern(pattern);
+
+              ++step;
+            } else if (step === 2) {
+              // found an AMEX card number
+              console.log('\nThere is an AMEX card number:\n  ' + result.out_str);
+
+              // change mode to find the owner of the credit card; supposedly, the owner's
+              // name proceeds the number
+              mode = await txtSearch.getMode();
+              mode += PDFNet.TextSearch.Mode.e_search_up;
+              txtSearch.setMode(mode);
+              pattern = '[A-z]++ [A-z]++';
+              txtSearch.setPattern(pattern);
+
+              ++step;
+            } else if (step === 3) {
+              // found the owner's name of the AMEX card
+              console.log("Is the owner's name:\n  " + result.out_str + '?');
+
+              // add a link annotation based on the location of the found instance
+              hlts = result.highlights;
+              await hlts.begin(doc); // is await needed?
+              while ((await hlts.hasNext())) {
+                const curPage = await doc.getPage((await hlts.getCurrentPageNumber()));
+                const quadArr = await hlts.getCurrentQuads();
+                for (let i = 0; i < quadArr.length; ++i) {
+                  const currQuad = quadArr[i];
+                  const x1 = Math.min(Math.min(Math.min(currQuad.p1x, currQuad.p2x), currQuad.p3x), currQuad.p4x);
+                  const x2 = Math.max(Math.max(Math.max(currQuad.p1x, currQuad.p2x), currQuad.p3x), currQuad.p4x);
+                  const y1 = Math.min(Math.min(Math.min(currQuad.p1y, currQuad.p2y), currQuad.p3y), currQuad.p4y);
+                  const y2 = Math.max(Math.max(Math.max(currQuad.p1y, currQuad.p2y), currQuad.p3y), currQuad.p4y);
+
+                  const hyperLink = await PDFNet.LinkAnnot.create(doc, (await PDFNet.Rect.init(x1, y1, x2, y2)));
+                  await hyperLink.setAction((await PDFNet.Action.createURI(doc, 'http://www.pdftron.com')));
+                  await curPage.annotPushBack(hyperLink);
+                }
+                hlts.next();
+              }
+              await doc.save('../../TestFiles/Output/credit card numbers_linked.pdf', PDFNet.SDFDoc.SaveOptions.e_linearized);
+              break;
+            }
+          } else if (result.code === PDFNet.TextSearch.ResultCode.e_page) {
+            // you can update your UI here, if needed
+            console.log('page end');
+          } else if (result.code === PDFNet.TextSearch.ResultCode.e_done) {
+            break;
+          }
+        }
+      } 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.runTextSearchTest();
+})(exports);
+// eslint-disable-next-line spaced-comment
+//# sourceURL=TextSearchTest.js

package/samples/TextSearchTest/TextSearchTest.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/U3DTest/NODEJS/RunTest.sh

@@ -0,0 +1,2 @@
+#!/bin/sh
+node U3DTest.js

package/samples/U3DTest/NODEJS/U3DTest.js

@@ -0,0 +1,105 @@
+//---------------------------------------------------------------------------------------
+// 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';
+
+  exports.runU3DTest = () => {
+    const input_path = '../../TestFiles/';
+
+    const create3DAnnotation = async (doc, annots) => {
+      // ---------------------------------------------------------------------------------
+      // Create a 3D annotation based on U3D content. PDF 1.6 introduces the capability 
+      // for collections of three-dimensional objects, such as those used by CAD software, 
+      // to be embedded in PDF files.
+      const link_3D = await doc.createIndirectDict();
+      link_3D.putName('Subtype', '3D');
+
+      // Annotation location on the page
+      const link_3D_rect = await PDFNet.Rect.init(25, 180, 585, 643);
+      link_3D.putRect('Rect', link_3D_rect.x1, link_3D_rect.y1,
+        link_3D_rect.x2, link_3D_rect.y2);
+      annots.pushBack(link_3D);
+
+      // The 3DA entry is an activation dictionary (see Table 9.34 in the PDF Reference Manual) 
+      // that determines how the state of the annotation and its associated artwork can change.
+      const activation_dict_3D = await link_3D.putDict('3DA');
+
+      // Set the annotation so that it is activated as soon as the page containing the 
+      // annotation is opened. Other options are: PV (page view) and XA (explicit) activation.
+      activation_dict_3D.putName('A', 'PO');
+
+      // Embed U3D Streams (3D Model/Artwork).
+      const u3d_file = await PDFNet.Filter.createMappedFileFromUString(input_path + 'dice.u3d');
+      const u3d_reader = await PDFNet.FilterReader.create(u3d_file);
+
+      // To embed 3D stream without compression, you can omit the second parameter in CreateIndirectStream.
+      const flateEncode = await PDFNet.Filter.createFlateEncode();
+      const u3d_data_dict = await doc.createIndirectStreamFromFilter(u3d_reader, flateEncode);
+      u3d_data_dict.putName('Subtype', 'U3D');
+      link_3D.put('3DD', u3d_data_dict);
+
+      // Set the initial view of the 3D artwork that should be used when the annotation is activated.
+      const view3D_dict = await link_3D.putDict('3DV');
+      view3D_dict.putString('IN', 'Unnamed');
+      view3D_dict.putString('XN', 'Default');
+      view3D_dict.putName('MS', 'M');
+      view3D_dict.putNumber('CO', 27.5);
+
+      // A 12-element 3D transformation matrix that specifies a position and orientation 
+      // of the camera in world coordinates.
+      const tr3d = await view3D_dict.putArray('C2W');
+      tr3d.pushBackNumber(1); tr3d.pushBackNumber(0); tr3d.pushBackNumber(0);
+      tr3d.pushBackNumber(0); tr3d.pushBackNumber(0); tr3d.pushBackNumber(-1);
+      tr3d.pushBackNumber(0); tr3d.pushBackNumber(1); tr3d.pushBackNumber(0);
+      tr3d.pushBackNumber(0); tr3d.pushBackNumber(-27.5); tr3d.pushBackNumber(0);
+
+      // Create annotation appearance stream, a thumbnail which is used during printing or
+      // in PDF processors that do not understand 3D data.
+      const ap_dict = await link_3D.putDict('AP');
+
+      const builder = await PDFNet.ElementBuilder.create();
+      const writer = await PDFNet.ElementWriter.create();
+
+      writer.begin(doc);
+
+      const thumb_pathname = input_path + 'dice.jpg';
+      const image = await PDFNet.Image.createFromFile(doc, thumb_pathname);
+      writer.writePlacedElement(await builder.createImageScaled(image, 0.0, 0.0, await link_3D_rect.width(), await link_3D_rect.height()));
+
+      const normal_ap_stream = await writer.end();
+      normal_ap_stream.putName('Subtype', 'Form');
+      normal_ap_stream.putRect('BBox', 0, 0, await link_3D_rect.width(), await link_3D_rect.height());
+      ap_dict.put('N', normal_ap_stream);
+    }
+
+    const main = async () => {
+      const output_path = '../../TestFiles/Output/';
+
+      try {
+        const doc = await PDFNet.PDFDoc.create();
+        const page = await doc.pageCreate();
+        doc.pagePushBack(page);
+        const annots = await doc.createIndirectArray();
+        page.getSDFObj().then(sdf => sdf.put('Annots', annots));
+
+        await create3DAnnotation(doc, annots);
+        doc.save(output_path + 'dice_u3d.pdf', PDFNet.SDFDoc.SaveOptions.e_linearized);
+        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.runU3DTest();
+})(exports);
+// eslint-disable-next-line spaced-comment
+//# sourceURL=U3DTest.js