OCR

1//---------------------------------------------------------------------------------------
2// Copyright (c) 2001-2019 by PDFTron Systems Inc. All Rights Reserved.
3// Consult legal.txt regarding legal and license information.
4//---------------------------------------------------------------------------------------
5
6#import <OBJC/PDFNetOBJC.h>
7#import <Foundation/Foundation.h>
8
9//---------------------------------------------------------------------------------------
10// The following sample illustrates how to use OCR module
11//---------------------------------------------------------------------------------------
12int main(int argc, char *argv[])
13{
14    @autoreleasepool {
15        @try
16        {
17            // The first step in every application using PDFNet is to initialize the 
18            // library and set the path to common PDF resources. The library is usually 
19            // initialized only once, but calling Initialize() multiple times is also fine.
20            [PTPDFNet Initialize: 0];
21
22			//--------------------------------------------------------------------------------
23			// Example 1) Process image without specifying options, default language - English - is used
24			
25            @try 
26            {
27                // A) Setup empty destination doc
28                
29				PTPDFDoc * doc = [[PTPDFDoc alloc] init];
30
31				// B) Run OCR on the .png with options
32
33				NSString * img = @"../../TestFiles/psychomachia_excerpt.png";
34				
35				[PTOCRModule ImageToPDF: doc src: img options: nil];
36
37				// C) check the result
38
39                NSString * outputFile = @"../../TestFiles/Output/psychomachia_excerpt.pdf";
40				[doc SaveToFile: outputFile flags: e_ptremove_unused];
41
42				NSLog(@"Example 1 psychomachia_excerpt.png\n");
43            }
44            @catch(NSException *e)	
45            {
46                NSLog(@"%@", e.reason);
47            }
48
49			//--------------------------------------------------------------------------------
50			// Example 2) Process document using multiple languages
51		
52            @try 
53            {
54                // A) Setup empty destination doc
55                
56				PTPDFDoc * doc = [[PTPDFDoc alloc] init];
57
58				// B) Setup options with multiple target languages, English will always be considered as secondary language
59
60				PTObjSet * set = [[PTObjSet alloc] init];
61				PTObj * options = [set CreateDict];
62				PTObj * lang_array = [options PutArray: @"Langs"];
63				[lang_array PushBackString: @"rus"];
64				[lang_array PushBackString: @"deu"];
65
66				// C) Run OCR on the .jpg with options
67
68				NSString * img = @"../../TestFiles/multi_lang.jpg";
69
70				[PTOCRModule ImageToPDF: doc src: img options: options];
71
72				// D) check the result
73
74                NSString * outputFile = @"../../TestFiles/Output/multi_lang.pdf";
75				[doc SaveToFile: outputFile flags: e_ptremove_unused];
76
77				NSLog(@"Example 2: multi_lang.jpg\n");
78            }
79            @catch(NSException *e)	
80            {
81                NSLog(@"%@", e.reason);
82            }
83
84			//--------------------------------------------------------------------------------
85			// Example 3) Process a .pdf specifying a language - German - and ignore zone comprising a sidebar image 
86			@try 
87            {
88                // A) Open the .pdf document
89                
90				PTPDFDoc * doc = [[PTPDFDoc alloc] initWithFilepath: @"../../TestFiles/german_kids_song.pdf"];
91
92			    // B) Setup options with a single language and an ignore zone
93
94				PTObjSet * set = [[PTObjSet alloc] init];
95				PTObj * options = [set CreateDict];
96				PTObj * lang_array = [options PutArray: @"Langs"];
97				[lang_array PushBackString: @"deu"];
98
99				PTObj * ignore_zones = [options PutArray: @"IgnoreZones"];
100				PTObj * ignore_zones_page1 = [ignore_zones PushBackArray];
101				[ignore_zones_page1 PushBackRect: 1768 y1: 680 x2: 2056 y2: 3044 ];
102
103			    // C) Run OCR on the .pdf with options
104
105				[PTOCRModule ProcessPDF: doc options: options];
106
107				// D) check the result
108
109                NSString * outputFile = @"../../TestFiles/Output/german_kids_song.pdf";
110				[doc SaveToFile: outputFile flags: e_ptremove_unused];
111
112				NSLog(@"Example 3: german_kids_song.pdf\n");
113            }
114            @catch(NSException *e)	
115            {
116                NSLog(@"%@", e.reason);
117            }
118
119
120			//--------------------------------------------------------------------------------
121			// Example 4) Process multipage tiff with text/ignore zones specified for each page, optionally provide English as the target language
122			@try 
123            {
124				// A) Setup empty destination doc
125                
126				PTPDFDoc * doc = [[PTPDFDoc alloc] init];
127
128				// B) Setup options with a single language plus text/ignore zones
129
130				PTObjSet * set = [[PTObjSet alloc] init];
131				PTObj * options = [set CreateDict];
132				PTObj * lang_array = [options PutArray: @"Langs"];
133				[lang_array PushBackString: @"eng"];
134
135				PTObj * ignore_zones = [options PutArray: @"IgnoreZones"];
136				PTObj * ignore_zones_page1 = [ignore_zones PushBackArray];
137				PTObj * ignore_zones_page2 = [ignore_zones PushBackArray];
138				PTObj * ignore_zones_page3 = [ignore_zones PushBackArray];
139
140				// ignore signature box in the first 2 pages
141				[ignore_zones_page1 PushBackRect: 1492 y1: 56 x2: 2236 y2: 432 ];
142				[ignore_zones_page2 PushBackRect: 1492 y1: 56 x2: 2236 y2: 432 ];
143
144				// can use a combination of ignore and text boxes to focus on the page area of interest,
145				// as ignore boxes are applied first, we remove the arrows before selecting part of the diagram
146				[ignore_zones_page3 PushBackRect: 992 y1: 1276 x2: 1368 y2: 1372 ];
147
148				PTObj * text_zones = [options PutArray: @"TextZones"];
149
150				// we only have text zones selected in page 3, so text_zones_page1 and text_zones_page2 will be empty
151				PTObj * text_zones_page1 = [text_zones PushBackArray];
152				PTObj * text_zones_page2 = [text_zones PushBackArray];
153				PTObj * text_zones_page3 = [text_zones PushBackArray];
154
155				// select horizontal BUFFER ZONE sign
156				[text_zones_page3 PushBackRect: 900 y1: 2384 x2: 1236 y2: 2480 ];
157
158				// select right vertical BUFFER ZONE sign
159				[text_zones_page3 PushBackRect: 1960 y1: 1976 x2: 2016 y2: 2296 ];
160
161				// select Lot No.
162				[text_zones_page3 PushBackRect: 696 y1: 1028 x2: 1196 y2: 1128 ];
163
164				// select part of the plan inside the BUFFER ZONE
165				[text_zones_page3 PushBackRect: 428 y1: 1484 x2: 1784 y2: 2344 ];
166				[text_zones_page3 PushBackRect: 948 y1: 1288 x2: 1672 y2: 1476 ];
167
168			    // C) Run OCR on the .pdf with options
169
170				NSString * img = @"../../TestFiles/bc_environment_protection.tif";
171
172				[PTOCRModule ImageToPDF: doc src: img options: options];
173
174				// D) check the result
175
176                NSString * outputFile = @"../../TestFiles/Output/bc_environment_protection.pdf";
177				[doc SaveToFile: outputFile flags: e_ptremove_unused];
178
179				NSLog(@"Example 4: bc_environment_protection.tif\n");
180            }
181            @catch(NSException *e)	
182            {
183                NSLog(@"%@", e.reason);
184            }
185
186			//--------------------------------------------------------------------------------
187			// Example 5) Alternative workflow for extracting OCR result JSON, postprocessing (e.g., removing words not in the dictionary or filtering special
188			// out special characters), and finally applying modified OCR JSON to the source PDF document 
189			@try 
190            {
191				// A) Open the .pdf document
192                
193				PTPDFDoc * doc = [[PTPDFDoc alloc] initWithFilepath: @"../../TestFiles/zero_value_test_no_text.pdf"];
194
195				// B) Run OCR on the .pdf with default English languages
196
197				NSString * json = [PTOCRModule GetOCRJsonFromPDF: doc options: nil];
198
199				// C) Post-processing step (whatever it might be), but we just print json here
200				
201			    NSLog(@"OCR result JSON: %@", json);
202
203				// D) Apply potentially modified OCR JSON to the PDF
204
205				[PTOCRModule ApplyOCRJsonToPDF: doc json: json];
206
207				// E) Check the result
208
209                NSString * outputFile = @"../../TestFiles/Output/zero_value_test_no_text.pdf";
210				[doc SaveToFile: outputFile flags: e_ptremove_unused];
211
212				NSLog(@"Example 5: extracting and applying OCR JSON from zero_value_test_no_text.pdf\n");
213            }
214            @catch(NSException *e)	
215            {
216                NSLog(@"%@", e.reason);
217            }
218
219		//--------------------------------------------------------------------------------
220		// Example 6) The postprocessing workflow has also an option of extracting OCR results in XML format, similar to the one used by TextExtractor
221		@try 
222		{
223
224			// A) Setup empty destination doc
225
226			PTPDFDoc * doc = [[PTPDFDoc alloc] init];
227
228			// B) Run OCR on the .tif with default English language, extracting OCR results in XML format. Note that
229			// in the process we convert the source image into PDF. We reuse this PDF document later to add hidden text layer to it.
230
231			NSString * img = @"../../TestFiles/physics.tif";
232
233			NSString * xml = [PTOCRModule GetOCRXmlFromImage: doc src: img options: nil];
234
235			// C) Post-processing step (whatever it might be), but we just print XML here
236
237			NSLog(@"OCR result XML: %@", xml);
238
239			// D) Apply potentially modified OCR XML to the PDF
240
241			[PTOCRModule ApplyOCRXmlToPDF: doc xml: xml];
242
243			// E) Check the result
244
245			NSString * outputFile = @"../../TestFiles/Output/physics.pdf";
246			[doc SaveToFile: outputFile flags: e_ptremove_unused];
247
248			NSLog(@"Example 6: extracting and applying OCR XML from physics.tif\n");
249
250		}
251		@catch(NSException *e)	
252        {
253            NSLog(@"%@", e.reason);
254        }
255
256        }
257        @catch(NSException *e)	
258        {
259            NSLog(@"%@", e.reason);
260        }
261
262        return 0;
263    }
264}