Objective-C Requires Chilkat v11.7.0+

Search a PDF with a Regular Expression

See more PDF Text Extraction Examples

Demonstrates searching a PDF with a regular expression (regex: true), limiting the number of results (maxResults), and matching whole words only (wholeWord). Objective-C

#import <CkoPdf.h>
#import <CkoJsonObject.h>

BOOL success = NO;

//  This example requires the Chilkat API to have been previously unlocked.
//  See Global Unlock Sample for sample code.

//  The PDF used in this example is available at order_records.pdf

CkoPdf *pdf = [[CkoPdf alloc] init];
success = [pdf LoadFile: @"qa_data/pdf/order_records.pdf"];
if (success == NO) {
    NSLog(@"%@",pdf.LastErrorText);
    return;
}

CkoJsonObject *json = [[CkoJsonObject alloc] init];
CkoJsonObject *jsonOut = [[CkoJsonObject alloc] init];

//  Find every order number.  With regex set to true, the query is a regular expression.
[json UpdateString: @"query" value: @"ORD-[0-9]{4}-[0-9]{4}"];
[json UpdateBool: @"regex" value: YES];
//  We only want the matched text, so no context is needed.
[json UpdateInt: @"context" value: [NSNumber numberWithInt: 0]];

success = [pdf ExtractText: @"search" jsonIn: json jsonOut: jsonOut];
if (success == NO) {
    NSLog(@"%@",pdf.LastErrorText);
    return;
}

NSLog(@"%@%d",@"Order numbers found: ",[[jsonOut IntOf: @"count"] intValue]);
int i = 0;
int count_i = [[jsonOut SizeOfArray: @"matches"] intValue];
while (i < count_i) {
    jsonOut.I = [NSNumber numberWithInt: i];
    NSLog(@"%@",[jsonOut StringOf: @"matches[i].text"]);
    i = i + 1;
}

//  Find the e-mail addresses, but stop after the first three.
[json UpdateString: @"query" value: @"[a-z0-9._]+@[a-z]+[.][a-z]+"];
[json UpdateInt: @"maxResults" value: [NSNumber numberWithInt: 3]];
success = [pdf ExtractText: @"search" jsonIn: json jsonOut: jsonOut];
if (success == NO) {
    NSLog(@"%@",pdf.LastErrorText);
    return;
}

NSLog(@"%@",@"First three e-mail addresses:");
i = 0;
count_i = [[jsonOut SizeOfArray: @"matches"] intValue];
while (i < count_i) {
    jsonOut.I = [NSNumber numberWithInt: i];
    NSLog(@"%@",[jsonOut StringOf: @"matches[i].text"]);
    i = i + 1;
}

//  wholeWord: true matches only whole words.  The word "cat" appears once in the PDF,
//  but it is also inside "catalog" and "category".
[json Delete: @"maxResults"];
[json UpdateBool: @"regex" value: NO];
[json UpdateString: @"query" value: @"cat"];
success = [pdf ExtractText: @"search" jsonIn: json jsonOut: jsonOut];
if (success == NO) {
    NSLog(@"%@",pdf.LastErrorText);
    return;
}

NSLog(@"%@%d",@"Occurrences of cat (any): ",[[jsonOut IntOf: @"count"] intValue]);

[json UpdateBool: @"wholeWord" value: YES];
success = [pdf ExtractText: @"search" jsonIn: json jsonOut: jsonOut];
if (success == NO) {
    NSLog(@"%@",pdf.LastErrorText);
    return;
}

NSLog(@"%@%d",@"Occurrences of cat (whole word): ",[[jsonOut IntOf: @"count"] intValue]);

//  Sample output:

//  Order numbers found: 9
//  ORD-2026-0301
//  ORD-2026-0302
//  ORD-2026-0303
//  ORD-2026-0304
//  ORD-2026-0305
//  ORD-2026-0306
//  ORD-2026-0307
//  ORD-2026-0308
//  ORD-2026-0307
//  First three e-mail addresses:
//  alice.moore@example.com
//  bkumar@example.org
//  carla@example.net
//  Occurrences of cat (any): 3
//  Occurrences of cat (whole word): 1