CAP-1609 Fixes for various samples for Python, Go, Ruby and PHP

PDFNetPHP/PDFNetPHP.i

@@ -288,6 +288,7 @@ namespace std {
    //%template(VectorString) vector<std::string>;
    %template(VectorRedaction) vector<pdftron::PDF::Redaction>;
    %template(VectorQuadPoint) vector<pdftron::PDF::QuadPoint>;
+   %template(VectorCharRange) vector<pdftron::PDF::CharRange>;
    %template(VectorSeparation) vector<pdftron::PDF::Separation>;
    %template(VectorDisallowedChange) vector<pdftron::PDF::DisallowedChange>;
    %template(VectorAnnot) vector<pdftron::PDF::Annot>;

PDFNetPython/PDFNetPython.i

@@ -283,6 +283,7 @@ namespace std {
    %template(VectorString) vector<std::string>;
    %template(VectorRedaction) vector<pdftron::PDF::Redaction>;
    %template(VectorQuadPoint) vector<pdftron::PDF::QuadPoint>;
+   %template(VectorCharRange) vector<pdftron::PDF::CharRange>;
    %template(VectorSeparation) vector<pdftron::PDF::Separation>;
    %template(VectorDisallowedChange) vector<pdftron::PDF::DisallowedChange>;
    %template(VectorAnnot) vector<pdftron::PDF::Annot>;

PDFNetRuby/PDFNetRuby.i

@@ -270,6 +270,7 @@ namespace std {
    %template(VectorString) vector<std::string>;
    %template(VectorRedaction) vector<pdftron::PDF::Redaction>;
    %template(VectorQuadPoint) vector<pdftron::PDF::QuadPoint>;
+   %template(VectorCharRange) vector<pdftron::PDF::CharRange>;
    %template(VectorSeparation) vector<pdftron::PDF::Separation>;
    %template(VectorDisallowedChange) vector<pdftron::PDF::DisallowedChange>;
    %template(VectorAnnot) vector<pdftron::PDF::Annot>;

PDFTronGo/pdftron.i

@@ -251,6 +251,7 @@ namespace std {
    %template(VectorString) vector<std::string>;
    %template(VectorRedaction) vector<pdftron::PDF::Redaction>;
    %template(VectorQuadPoint) vector<pdftron::PDF::QuadPoint>;
+   %template(VectorCharRange) vector<pdftron::PDF::CharRange>;
    %template(VectorSeparation) vector<pdftron::PDF::Separation>;
    %template(VectorDisallowedChange) vector<pdftron::PDF::DisallowedChange>;
    %template(VectorAnnot) vector<pdftron::PDF::Annot>;

Samples/DataExtractionTest/GO/DataExtraction_test.go

@@ -282,14 +282,14 @@ func GenericKeyValueTest() (err error) {
 	// 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.AddRect(NewRect(166, 47, 562, 222))
+	p2ExclusionZones.AddRect(NewRect(166.0, 47.0, 562.0, 222.0))
 	options.AddExclusionZonesForPage(p2ExclusionZones, 2)
 
 	p4InclusionZones := NewRectCollection()
 	p4ExclusionZones := NewRectCollection()
 	// Only include the article text for page 4, exclude ads and headings
-	p4InclusionZones.AddRect(NewRect(30, 432, 562, 684))
-	p4ExclusionZones.AddRect(NewRect(30, 657, 295, 684))
+	p4InclusionZones.AddRect(NewRect(30.0, 432.0, 562.0, 684.0))
+	p4ExclusionZones.AddRect(NewRect(30.0, 657.0, 295.0, 684.0))
 	options.AddInclusionZonesForPage(p4InclusionZones, 4)
 	options.AddExclusionZonesForPage(p4ExclusionZones, 4)
 

Samples/EncTest/GO/Enc_test.go

@@ -90,8 +90,7 @@ func TestEnc(t *testing.T){
         for count < 3{
             fmt.Println("A password required to open the document.")
             var password string
-            fmt.Print("Please enter the password: \n")
-            fmt.Scanf("%s", &password)
+            password = userPassword
             fmt.Println(password)
 
             if doc.InitStdSecurityHandler(password, len(password)){

Samples/EncTest/PHP/EncTest.php

@@ -80,9 +80,8 @@
 		for($count=0; $count<3;$count++)
 		{
 			echo "A password required to open the document.\n"
-				."Please enter the password:";
 
-			$password = trim(fgets(STDIN));
+			$password = "test";
 			if($doc->InitStdSecurityHandler($password, strlen($password)))
 			{
 				$success=true;

Samples/EncTest/PYTHON/EncTest.py

@@ -84,9 +84,9 @@ def main():
         while count < 3:
             print("A password required to open the document.")
             if sys.version_info.major >= 3:
-                password = input("Please enter the password: \n")
+                password = "test"
             else:
-                password = raw_input("Please enter the password: \n")
+                password = "test"
 
             if doc.InitStdSecurityHandler(password, len(password)):
                 success = True

Samples/EncTest/RUBY/EncTest.rb

@@ -81,8 +81,7 @@
 		count = 0
 		while count < 3 do
 			puts "A password required to open the document."
-			puts "Please enter the password:"
-			password = gets.chomp
+			password = "test"
 			if doc.InitStdSecurityHandler(password, password.length)
 				success = true
 				puts "The password is correct."

Samples/HighlightsTest/GO/Highlights_test.go

@@ -0,0 +1,117 @@
+//---------------------------------------------------------------------------------------
+// Copyright (c) 2001-2026 by Apryse Software Inc. All Rights Reserved.
+// Consult LICENSE.txt regarding license information.
+//---------------------------------------------------------------------------------------
+
+package main
+
+import (
+	"flag"
+	"fmt"
+	"math"
+	"strings"
+	"testing"
+
+	. "github.com/pdftron/pdftron-go/v2"
+)
+
+var licenseKey string
+var modulePath string
+
+func init() {
+	flag.StringVar(&licenseKey, "license", "", "License key for Apryse SDK")
+	flag.StringVar(&modulePath, "modulePath", "", "Module path for Apryse SDK")
+}
+
+// ---------------------------------------------------------------------------------------
+// This sample illustrates the basic text highlight capabilities of PDFNet.
+// It simulates a full-text search engine that finds all occurrences of the word 'Federal'.
+// It then highlights those words on the page.
+//
+// Note: The TextSearch class is the preferred solution for searching text within a single
+// PDF file. TextExtractor provides search highlighting capabilities where a large number
+// of documents are indexed using a 3rd party search engine.
+// --------------------------------------------------------------------------------------
+
+func TestHighlights(t *testing.T) {
+	// The first step in every application using PDFNet is to initialize the
+	// library and set the path to common PDF resources. The library is usually
+	// initialized only once, but calling Initialize() multiple times is also fine.
+	PDFNetInitialize(licenseKey)
+
+	// Relative path to the folder containing the test files.
+	inputPath := "../TestFiles/paragraphs_and_tables.pdf"
+	outputPath := "../TestFiles/Output/"
+
+	// Sample code showing how to use high-level text highlight APIs.
+	doc := NewPDFDoc(inputPath)
+	doc.InitSecurityHandler()
+
+	page := doc.GetPage(1)
+	if !page.IsValid() {
+		PDFNetTerminate()
+		t.Fatal("Page not found.")
+	}
+
+	txt := NewTextExtractor()
+	txt.Begin(page) // read the page
+
+	// Do not dehyphenate; that would interfere with character offsets
+	dehyphen := false
+
+	// Retrieve the page text
+	pageText := txt.GetAsText(dehyphen)
+
+	// Simulating a full-text search engine that finds all occurrences of the word 'Federal'.
+	// In a real application, plug in your own search engine here.
+	searchText := "Federal"
+
+	charRanges := NewVectorCharRange()
+	ofs := strings.Index(pageText, searchText)
+	for ofs != -1 {
+		cr := NewCharRange()
+		cr.SetIndex(ofs)
+		cr.SetLength(len(searchText))
+		charRanges.Add(cr)
+		next := strings.Index(pageText[ofs+1:], searchText)
+		if next == -1 {
+			break
+		}
+		ofs = ofs + 1 + next
+	}
+
+	// Retrieve Highlights object and apply annotations to the page
+	hlts := txt.GetHighlights(charRanges)
+	hlts.Begin(doc)
+
+	for hlts.HasNext() {
+		quads := hlts.GetCurrentQuads()
+		count := int(quads.Size())
+		for i := 0; i < count; i++ {
+			q := quads.Get(i)
+
+			// Each quad has 4 points: q.P1, q.P2, q.P3, q.P4
+			x1 := math.Min(math.Min(q.GetP1().GetX(), q.GetP2().GetX()), math.Min(q.GetP3().GetX(), q.GetP4().GetX()))
+			x2 := math.Max(math.Max(q.GetP1().GetX(), q.GetP2().GetX()), math.Max(q.GetP3().GetX(), q.GetP4().GetX()))
+			y1 := math.Min(math.Min(q.GetP1().GetY(), q.GetP2().GetY()), math.Min(q.GetP3().GetY(), q.GetP4().GetY()))
+			y2 := math.Max(math.Max(q.GetP1().GetY(), q.GetP2().GetY()), math.Max(q.GetP3().GetY(), q.GetP4().GetY()))
+
+			highlight := pdftron.HighlightAnnotCreate(
+				doc.GetSDFDoc(),
+				pdftron.NewRect(x1, y1, x2, y2),
+			)
+			highlight.RefreshAppearance()
+			page.AnnotPushBack(highlight)
+
+			fmt.Printf("[%.2f, %.2f, %.2f, %.2f]\n", x1, y1, x2, y2)
+		}
+
+		hlts.Next()
+	}
+	doc.Save(outputPath+"search_highlights.pdf", uint(SDFDocE_linearized))
+
+	doc.Close()
+
+	PDFNetTerminate()
+	fmt.Println("Done.")
+}

Samples/HighlightsTest/PHP/HighlightsTest.php

@@ -0,0 +1,109 @@
+<?php
+//---------------------------------------------------------------------------------------
+// Copyright (c) 2001-2026 by Apryse Software Inc. All Rights Reserved.
+// Consult LICENSE.txt regarding license information.
+//---------------------------------------------------------------------------------------
+if(file_exists("../../../PDFNetC/Lib/PDFNetPHP.php"))
+include("../../../PDFNetC/Lib/PDFNetPHP.php");
+include("../../LicenseKey/PHP/LicenseKey.php");
+
+// Relative path to the folder containing the test files.
+$input_path = getcwd()."/../../TestFiles/paragraphs_and_tables.pdf";
+$output_path = getcwd()."../../TestFiles/Output/";
+
+//---------------------------------------------------------------------------------------
+// This sample illustrates the basic text highlight capabilities of PDFNet.
+// It simulates a full-text search engine that finds all occurrences of the word 'Federal'.
+// It then highlights those words on the page.
+// 
+// Note: The TextSearch class is the preferred solution for searching text within a single
+// PDF file. TextExtractor provides search highlighting capabilities where a large number
+// of documents are indexed using a 3rd party search engine.
+// --------------------------------------------------------------------------------------
+
+	// The first step in every application using PDFNet is to initialize the
+    // library and set the path to common PDF resources. The library is usually
+    // initialized only once, but calling Initialize() multiple times is also fine.
+	PDFNet::Initialize($LicenseKey);
+
+	$example1_basic     = false;
+	$example2_xml       = false;
+	$example3_wordlist  = false;
+	$example4_advanced  = true;
+	$example5_low_level = false;
+
+	// Sample code showing how to use high-level text extraction APIs.
+	$doc = new PDFDoc($input_path);
+	$doc->InitSecurityHandler();
+
+	$page = $doc->GetPage(1);
+	if (!$page){
+		echo nl2br("Page not found.\n");
+		PDFNet::Terminate();
+		return;
+	}
+
+	$txt = new TextExtractor();
+	$txt->Begin($page); // Read the page.
+
+	// Do not dehyphenate; that would interfere with character offsets
+    $dehyphen = false;
+    # Retrieve the page text
+    $page_text = $txt->GetAsText($dehyphen);
+
+	// Simulating a full-text search engine that finds all occurrences of the word 'Federal'.
+    // In a real application, plug in your own search engine here.
+    $search_text = "Federal";
+	$char_ranges = [];
+
+	$ofs = strpos($page_text, $search_text);
+	while ($ofs !== false) {
+		$cr = new CharRange();
+		$cr->index = $ofs;
+		$cr->length = strlen($search_text);
+		$char_ranges[] = $cr;
+		$ofs = strpos($page_text, $search_text, $ofs + 1);
+	}
+
+	// Retrieve Highlights object and apply annotations to the page
+	$hlts = $txt->GetHighlights($char_ranges);
+	$hlts->Begin($doc);
+
+	while ($hlts->HasNext()) {
+
+		// In PHP bindings, quads are typically returned as an array
+		$quads = $hlts->GetCurrentQuads();
+		$quad_count = count($quads);
+
+		for ($i = 0; $i < $quad_count; $i++) {
+
+			// Each quad has 4 points: p1, p2, p3, p4
+			$q = $quads[$i];
+
+			$x1 = min($q->p1->x, $q->p2->x, $q->p3->x, $q->p4->x);
+			$x2 = max($q->p1->x, $q->p2->x, $q->p3->x, $q->p4->x);
+			$y1 = min($q->p1->y, $q->p2->y, $q->p3->y, $q->p4->y);
+			$y2 = max($q->p1->y, $q->p2->y, $q->p3->y, $q->p4->y);
+
+			$highlight = HighlightAnnot::Create(
+				$doc->GetSDFDoc(),
+				new Rect($x1, $y1, $x2, $y2)
+			);
+
+			$highlight->RefreshAppearance();
+			$page->AnnotPushBack($highlight);
+
+			printf("[%.2f, %.2f, %.2f, %.2f]\n", $x1, $y1, $x2, $y2);
+		}
+
+		$hlts->Next();
+	}
+
+	// Output highlighted PDF doc
+	$doc->Save($output_path . "search_highlights.pdf", SDFDoc::e_linearized);
+
+	$doc->Close();
+	echo nl2br("Done.\n");
+
+	PDFNet::Terminate();
+?>

Samples/HighlightsTest/PHP/RunTest.bat

@@ -0,0 +1,6 @@
+@echo off
+setlocal
+set TEST_NAME=HighlightsTest
+set PATH=..\..\..\PDFNetC\Lib;%PATH%
+php.exe %TEST_NAME%.php
+endlocal

Samples/HighlightsTest/PHP/RunTest.sh

@@ -0,0 +1,4 @@
+#!/bin/sh
+TEST_NAME=HighlightsTest
+export LD_LIBRARY_PATH=../../../PDFNetC/Lib
+php -d extension="../../../PDFNetC/Lib/PDFNetPHP.so" $TEST_NAME.php