Lesen von Tabellen in Dokumenten mit C#

using IronOcr;
using System;
using System.Data;

// Instantiate OCR engine
var ocr = new IronTesseract();

// Enable table detection
ocr.Configuration.ReadDataTables = true;

using var input = new OcrPdfInput("simple-table.pdf");
var result = ocr.Read(input);

// Retrieve the data
var table = result.Tables[0].DataTable;

// Print out the table data
foreach (DataRow row in table.Rows)
{
    foreach (var item in row.ItemArray)
    {
        Console.Write(item + "\t");
    }
    Console.WriteLine();
}

using IronOcr;
using System;
using System.Data;

// Instantiate OCR engine
var ocr = new IronTesseract();

// Enable table detection
ocr.Configuration.ReadDataTables = true;

using var input = new OcrPdfInput("simple-table.pdf");
var result = ocr.Read(input);

// Retrieve the data
var table = result.Tables[0].DataTable;

// Print out the table data
foreach (DataRow row in table.Rows)
{
    foreach (var item in row.ItemArray)
    {
        Console.Write(item + "\t");
    }
    Console.WriteLine();
}

using IronOcr;
using System.Linq;

// Instantiate OCR engine
var ocr = new IronTesseract();

using var input = new OcrInput();
input.LoadPdf("invoiceTable.pdf");

// Perform OCR
var result = ocr.ReadDocumentAdvanced(input);

var cellList = result.Tables.First().CellInfos;

using IronOcr;
using System.Linq;

// Instantiate OCR engine
var ocr = new IronTesseract();

using var input = new OcrInput();
input.LoadPdf("invoiceTable.pdf");

// Perform OCR
var result = ocr.ReadDocumentAdvanced(input);

var cellList = result.Tables.First().CellInfos;

using System;
using System.Collections.Generic;
using System.Linq;

// A helper class to process table data by sorting cells based on coordinates
public static class TableProcessor
{
    // Method to organize cells by their coordinates (Y top to bottom, X left to right)
    public static List<CellInfo> OrganizeCellsByCoordinates(List<CellInfo> cells)
    {
        // Sort cells by Y (top to bottom), then by X (left to right)
        var sortedCells = cells
            .OrderBy(cell => cell.CellRect.Y)
            .ThenBy(cell => cell.CellRect.X)
            .ToList();

        return sortedCells;
    }

    // Example method demonstrating how to process multiple tables
    public static void ProcessTables(Tables tables)
    {
        foreach (var table in tables)
        {
            var sortedCells = OrganizeCellsByCoordinates(table.CellInfos);

            Console.WriteLine("Organized Table Cells:");

            // Initialize previous Y coordinate
            int previousY = sortedCells.Any() ? sortedCells.First().CellRect.Y : 0;

            foreach (var cell in sortedCells)
            {
                // Print a new line if the Y-coordinate changes, indicating a new row
                if (Math.Abs(cell.CellRect.Y - previousY) > cell.CellRect.Height * 0.8)
                {
                    Console.WriteLine();  // Start a new row
                    previousY = cell.CellRect.Y;
                }

                // Print the cell text followed by a tab
                Console.Write($"{cell.CellText}\t");
            }

            Console.WriteLine("\n--- End of Table ---");  // End of a table
        }
    }

    // Method to extract a specific row by the given index
    public static List<CellInfo> ExtractRowByIndex(TableInfo table, int rowIndex)
    {
        if (table == null || table.CellInfos == null || !table.CellInfos.Any())
        {
            throw new ArgumentException("Table is empty or invalid.");
        }

        var sortedCells = OrganizeCellsByCoordinates(table.CellInfos);
        List<List<CellInfo>> rows = new List<List<CellInfo>>();

        // Group cells into rows based on Y coordinates
        int previousY = sortedCells.First().CellRect.Y;
        List<CellInfo> currentRow = new List<CellInfo>();

        foreach (var cell in sortedCells)
        {
            if (Math.Abs(cell.CellRect.Y - previousY) > cell.CellRect.Height * 0.8)
            {
                // Store the completed row and start a new one
                rows.Add(new List<CellInfo>(currentRow));
                currentRow.Clear();

                previousY = cell.CellRect.Y;
            }

            currentRow.Add(cell);
        }

        // Add the last row if it wasn't added yet
        if (currentRow.Any())
        {
            rows.Add(currentRow);
        }

        // Retrieve the specified row
        if (rowIndex < 0 || rowIndex >= rows.Count)
        {
            throw new IndexOutOfRangeException($"Row index {rowIndex} is out of range.");
        }

        return rows[rowIndex];
    }
}

using System;
using System.Collections.Generic;
using System.Linq;

// A helper class to process table data by sorting cells based on coordinates
public static class TableProcessor
{
    // Method to organize cells by their coordinates (Y top to bottom, X left to right)
    public static List<CellInfo> OrganizeCellsByCoordinates(List<CellInfo> cells)
    {
        // Sort cells by Y (top to bottom), then by X (left to right)
        var sortedCells = cells
            .OrderBy(cell => cell.CellRect.Y)
            .ThenBy(cell => cell.CellRect.X)
            .ToList();

        return sortedCells;
    }

    // Example method demonstrating how to process multiple tables
    public static void ProcessTables(Tables tables)
    {
        foreach (var table in tables)
        {
            var sortedCells = OrganizeCellsByCoordinates(table.CellInfos);

            Console.WriteLine("Organized Table Cells:");

            // Initialize previous Y coordinate
            int previousY = sortedCells.Any() ? sortedCells.First().CellRect.Y : 0;

            foreach (var cell in sortedCells)
            {
                // Print a new line if the Y-coordinate changes, indicating a new row
                if (Math.Abs(cell.CellRect.Y - previousY) > cell.CellRect.Height * 0.8)
                {
                    Console.WriteLine();  // Start a new row
                    previousY = cell.CellRect.Y;
                }

                // Print the cell text followed by a tab
                Console.Write($"{cell.CellText}\t");
            }

            Console.WriteLine("\n--- End of Table ---");  // End of a table
        }
    }

    // Method to extract a specific row by the given index
    public static List<CellInfo> ExtractRowByIndex(TableInfo table, int rowIndex)
    {
        if (table == null || table.CellInfos == null || !table.CellInfos.Any())
        {
            throw new ArgumentException("Table is empty or invalid.");
        }

        var sortedCells = OrganizeCellsByCoordinates(table.CellInfos);
        List<List<CellInfo>> rows = new List<List<CellInfo>>();

        // Group cells into rows based on Y coordinates
        int previousY = sortedCells.First().CellRect.Y;
        List<CellInfo> currentRow = new List<CellInfo>();

        foreach (var cell in sortedCells)
        {
            if (Math.Abs(cell.CellRect.Y - previousY) > cell.CellRect.Height * 0.8)
            {
                // Store the completed row and start a new one
                rows.Add(new List<CellInfo>(currentRow));
                currentRow.Clear();

                previousY = cell.CellRect.Y;
            }

            currentRow.Add(cell);
        }

        // Add the last row if it wasn't added yet
        if (currentRow.Any())
        {
            rows.Add(currentRow);
        }

        // Retrieve the specified row
        if (rowIndex < 0 || rowIndex >= rows.Count)
        {
            throw new IndexOutOfRangeException($"Row index {rowIndex} is out of range.");
        }

        return rows[rowIndex];
    }
}