Obj-C use OCR to make searchable PDFs and extract text

//---------------------------------------------------------------------------------------
// Copyright (c) 2001-2019 by PDFTron Systems Inc. All Rights Reserved.
// Consult legal.txt regarding legal and license information.
//---------------------------------------------------------------------------------------

#import <OBJC/PDFNetOBJC.h>
#import <Foundation/Foundation.h>

//---------------------------------------------------------------------------------------
// The following sample illustrates how to use OCR module
//---------------------------------------------------------------------------------------
int main(int argc, char *argv[])
{
    @autoreleasepool {
        @try
        {
            // 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.
            [PTPDFNet Initialize: 0];

			//--------------------------------------------------------------------------------
			// Example 1) Process image without specifying options, default language - English - is used
			
            @try 
            {
                // A) Setup empty destination doc
                
				PTPDFDoc * doc = [[PTPDFDoc alloc] init];

				// B) Run OCR on the .png with options

				NSString * img = @"../../TestFiles/psychomachia_excerpt.png";
				
				[PTOCRModule ImageToPDF: doc src: img options: nil];

				// C) check the result

                NSString * outputFile = @"../../TestFiles/Output/psychomachia_excerpt.pdf";
				[doc SaveToFile: outputFile flags: e_ptremove_unused];

				NSLog(@"Example 1 psychomachia_excerpt.png\n");
            }
            @catch(NSException *e)	
            {
                NSLog(@"%@", e.reason);
            }

			//--------------------------------------------------------------------------------
			// Example 2) Process document using multiple languages
		
            @try 
            {
                // A) Setup empty destination doc
                
				PTPDFDoc * doc = [[PTPDFDoc alloc] init];

				// B) Setup options with multiple target languages, English will always be considered as secondary language

				PTObjSet * set = [[PTObjSet alloc] init];
				PTObj * options = [set CreateDict];
				PTObj * lang_array = [options PutArray: @"Langs"];
				[lang_array PushBackString: @"rus"];
				[lang_array PushBackString: @"deu"];

				// C) Run OCR on the .jpg with options

				NSString * img = @"../../TestFiles/multi_lang.jpg";

				[PTOCRModule ImageToPDF: doc src: img options: options];

				// D) check the result

                NSString * outputFile = @"../../TestFiles/Output/multi_lang.pdf";
				[doc SaveToFile: outputFile flags: e_ptremove_unused];

				NSLog(@"Example 2: multi_lang.jpg\n");
            }
            @catch(NSException *e)	
            {
                NSLog(@"%@", e.reason);
            }

			//--------------------------------------------------------------------------------
			// Example 3) Process a .pdf specifying a language - German - and ignore zone comprising a sidebar image 
			@try 
            {
                // A) Open the .pdf document
                
				PTPDFDoc * doc = [[PTPDFDoc alloc] initWithFilepath: @"../../TestFiles/german_kids_song.pdf"];

			    // B) Setup options with a single language and an ignore zone

				PTObjSet * set = [[PTObjSet alloc] init];
				PTObj * options = [set CreateDict];
				PTObj * lang_array = [options PutArray: @"Langs"];
				[lang_array PushBackString: @"deu"];

				PTObj * ignore_zones = [options PutArray: @"IgnoreZones"];
				PTObj * ignore_zones_page1 = [ignore_zones PushBackArray];
				[ignore_zones_page1 PushBackRect: 1768 y1: 680 x2: 2056 y2: 3044 ];

			    // C) Run OCR on the .pdf with options

				[PTOCRModule ProcessPDF: doc options: options];

				// D) check the result

                NSString * outputFile = @"../../TestFiles/Output/german_kids_song.pdf";
				[doc SaveToFile: outputFile flags: e_ptremove_unused];

				NSLog(@"Example 3: german_kids_song.pdf\n");
            }
            @catch(NSException *e)	
            {
                NSLog(@"%@", e.reason);
            }


			//--------------------------------------------------------------------------------
			// 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
                
				PTPDFDoc * doc = [[PTPDFDoc alloc] init];

				// B) Setup options with a single language plus text/ignore zones

				PTObjSet * set = [[PTObjSet alloc] init];
				PTObj * options = [set CreateDict];
				PTObj * lang_array = [options PutArray: @"Langs"];
				[lang_array PushBackString: @"eng"];

				PTObj * ignore_zones = [options PutArray: @"IgnoreZones"];
				PTObj * ignore_zones_page1 = [ignore_zones PushBackArray];
				PTObj * ignore_zones_page2 = [ignore_zones PushBackArray];
				PTObj * ignore_zones_page3 = [ignore_zones PushBackArray];

				// ignore signature box in the first 2 pages
				[ignore_zones_page1 PushBackRect: 1492 y1: 56 x2: 2236 y2: 432 ];
				[ignore_zones_page2 PushBackRect: 1492 y1: 56 x2: 2236 y2: 432 ];

				// 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_page3 PushBackRect: 992 y1: 1276 x2: 1368 y2: 1372 ];

				PTObj * text_zones = [options PutArray: @"TextZones"];

				// we only have text zones selected in page 3, so text_zones_page1 and text_zones_page2 will be empty
				PTObj * text_zones_page1 = [text_zones PushBackArray];
				PTObj * text_zones_page2 = [text_zones PushBackArray];
				PTObj * text_zones_page3 = [text_zones PushBackArray];

				// select horizontal BUFFER ZONE sign
				[text_zones_page3 PushBackRect: 900 y1: 2384 x2: 1236 y2: 2480 ];

				// select right vertical BUFFER ZONE sign
				[text_zones_page3 PushBackRect: 1960 y1: 1976 x2: 2016 y2: 2296 ];

				// select Lot No.
				[text_zones_page3 PushBackRect: 696 y1: 1028 x2: 1196 y2: 1128 ];

				// select part of the plan inside the BUFFER ZONE
				[text_zones_page3 PushBackRect: 428 y1: 1484 x2: 1784 y2: 2344 ];
				[text_zones_page3 PushBackRect: 948 y1: 1288 x2: 1672 y2: 1476 ];

			    // C) Run OCR on the .pdf with options

				NSString * img = @"../../TestFiles/bc_environment_protection.tif";

				[PTOCRModule ImageToPDF: doc src: img options: options];

				// D) check the result

                NSString * outputFile = @"../../TestFiles/Output/bc_environment_protection.pdf";
				[doc SaveToFile: outputFile flags: e_ptremove_unused];

				NSLog(@"Example 4: bc_environment_protection.tif\n");
            }
            @catch(NSException *e)	
            {
                NSLog(@"%@", e.reason);
            }

			//--------------------------------------------------------------------------------
			// 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
                
				PTPDFDoc * doc = [[PTPDFDoc alloc] initWithFilepath: @"../../TestFiles/zero_value_test_no_text.pdf"];

				// B) Run OCR on the .pdf with default English languages

				NSString * json = [PTOCRModule GetOCRJsonFromPDF: doc options: nil];

				// C) Post-processing step (whatever it might be), but we just print json here
				
			    NSLog(@"OCR result JSON: %@", json);

				// D) Apply potentially modified OCR JSON to the PDF

				[PTOCRModule ApplyOCRJsonToPDF: doc json: json];

				// E) Check the result

                NSString * outputFile = @"../../TestFiles/Output/zero_value_test_no_text.pdf";
				[doc SaveToFile: outputFile flags: e_ptremove_unused];

				NSLog(@"Example 5: extracting and applying OCR JSON from zero_value_test_no_text.pdf\n");
            }
            @catch(NSException *e)	
            {
                NSLog(@"%@", e.reason);
            }

		//--------------------------------------------------------------------------------
		// 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

			PTPDFDoc * doc = [[PTPDFDoc alloc] init];

			// 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.

			NSString * img = @"../../TestFiles/physics.tif";

			NSString * xml = [PTOCRModule GetOCRXmlFromImage: doc src: img options: nil];

			// C) Post-processing step (whatever it might be), but we just print XML here

			NSLog(@"OCR result XML: %@", xml);

			// D) Apply potentially modified OCR XML to the PDF

			[PTOCRModule ApplyOCRXmlToPDF: doc xml: xml];

			// E) Check the result

			NSString * outputFile = @"../../TestFiles/Output/physics.pdf";
			[doc SaveToFile: outputFile flags: e_ptremove_unused];

			NSLog(@"Example 6: extracting and applying OCR XML from physics.tif\n");

		}
		@catch(NSException *e)	
        {
            NSLog(@"%@", e.reason);
        }

        }
        @catch(NSException *e)	
        {
            NSLog(@"%@", e.reason);
        }

        return 0;
    }
}