Link Search Menu Expand Document

Parse Multipage Table - Delphi

Document Parser SDK sample in Delphi demonstrating ‘Parse Multipage Table’

MultiPageTable-template1.yml
templateName: Multipage Table Test
templateVersion: 4
templatePriority: 0
detectionRules:
  keywords:
  - Sample document with multi-page table
objects:
- name: total
  objectType: field
  fieldProperties:
    fieldType: macros
    expression: TOTAL{{Spaces}}({{Number}})
    regex: true
    dataType: decimal
- name: table1
  objectType: table
  tableProperties:
    start:
      expression: Item{{Spaces}}Description{{Spaces}}Price
      regex: true
    end:
      expression: TOTAL{{Spaces}}{{Number}}
      regex: true
    row:
      expression: '{{LineStart}}{{Spaces}}(?<itemNo>{{Digits}}){{Spaces}}(?<description>{{SentenceWithSingleSpaces}}){{Spaces}}(?<price>{{Number}}){{Spaces}}(?<qty>{{Digits}}){{Spaces}}(?<extPrice>{{Number}})'
      regex: true
    columns:
    - name: itemNo
      dataType: integer
    - name: description
      dataType: string
    - name: price
      dataType: decimal
    - name: qty
      dataType: integer
    - name: extPrice
      dataType: decimal
    multipage: true


MultiPageTable-template2.yml
templateName: Multipage Table Test
templateVersion: 4
templatePriority: 0
detectionRules:
  keywords:
  - Sample document with multi-page table
objects:
- name: total
  objectType: field
  fieldProperties:
    fieldType: regex
    expression: TOTAL{{Spaces}}({{Number}})
    regex: true
    dataType: decimal
- name: table1
  objectType: table
  tableProperties:
    start:
      expression: Item{{Spaces}}Description{{Spaces}}Price
      regex: true
    end:
      expression: (Page {{Digits}} of {{Digits}})|(TOTAL{{Spaces}}{{Number}})
      regex: true
    left: 51
    right: 528
    columns:
    - x: 51
      name: itemNo
      dataType: integer
    - x: 102
      name: description
      dataType: string
    - x: 324
      name: price
      dataType: decimal
    - x: 396
      name: qty
      dataType: integer
    - x: 441
      name: extPrice
      dataType: decimal
    multipage: true


ParseMultipageTable.dpr
program ParseMultipageTable;

//*******************************************************************************************//
//                                                                                           //
// Download Free Evaluation Version From: https://bytescout.com/download/web-installer       //
//                                                                                           //
// Also available as Web API! Get Your Free API Key: https://app.pdf.co/signup               //
//                                                                                           //
// Copyright � 2017-2020 ByteScout, Inc. All rights reserved.                                //
// https://www.bytescout.com                                                                 //
// https://pdf.co                                                                            //
//                                                                                           //
//*******************************************************************************************//

{$APPTYPE CONSOLE}

// This example demonstrates parsing of multipage tables in two different approaches.
// See comments in the code of templates.

uses
  SysUtils,
  ActiveX,
  ByteScout_DocumentParser_TLB in 'C:\Program Files\Borland\BDS\4.0\Imports\ByteScout_DocumentParser_TLB.pas';

var
  document_parser: _DocumentParser;

const
  INPUT_DOCUMENT: string = 'MultiPageTable.pdf';
  CUSTOM_TEMPLATE1: string = 'MultiPageTable-template1.yml';
  CUSTOM_TEMPLATE2: string = 'MultiPageTable-template2.yml';
  OUTPUT_FILE_NAME1: string = 'result1.json';
  OUTPUT_FILE_NAME2: string = 'result2.json';

begin
  // disable floating point exception to conform to .NET floating point operations behavior.
  System.Set8087CW($133F);

  // required for console applications, initializes ActiveX support
  CoInitialize(nil);

  // create and activate DocumentParser instance
  document_parser := CoDocumentParser.Create();
  document_parser.RegistrationName := 'demo';
  document_parser.RegistrationKey := 'demo';

  WriteLn('Loading template 1...');
  document_parser.AddTemplate(CUSTOM_TEMPLATE1);

  WriteLn('Template 1 loaded.');
  WriteLn('');

  WriteLn('Parsing ' + INPUT_DOCUMENT + '...');
  WriteLn('');

  // parse document data in JSON format
  document_parser.ParseDocument_3(INPUT_DOCUMENT, OUTPUT_FILE_NAME1, OutputFormat_JSON, false);

  WriteLn('Parsing results saved to ' + OUTPUT_FILE_NAME1);
  WriteLn('');

  document_parser.Dispose();

  document_parser := CoDocumentParser.Create();
  document_parser.RegistrationName := 'demo';
  document_parser.RegistrationKey := 'demo';

  WriteLn('Loading template 2...');
  document_parser.AddTemplate(CUSTOM_TEMPLATE2);

  WriteLn('Template 2 loaded.');
  WriteLn('');

  WriteLn('Parsing ' + INPUT_DOCUMENT + '...');
  WriteLn('');

  // parse document data in JSON format
  document_parser.ParseDocument_3(INPUT_DOCUMENT, OUTPUT_FILE_NAME2, OutputFormat_JSON, false);

  WriteLn('Parsing results saved to ' + OUTPUT_FILE_NAME2);
  WriteLn('');

  document_parser.Dispose();

  CoUninitialize();
end.

Download Source Code (.zip)

Return to the previous page Explore Document Parser SDK


Copyright © 2016 - 2021 ByteScout