Extract the layout of a document

This sample demonstrates how to extract text, paragraphs, styles, table structures, and selection marks, along with their bounding region coordinates from documents. If you want to analyze key-value pairs in addition to this data, please see the Analyze with the prebuilt general document model sample.

To get started you'll need a Cognitive Services resource or a Form Recognizer resource. See README for prerequisites and instructions.

Creating a `DocumentAnalysisClient`

To create a new DocumentAnalysisClient you need the endpoint and credentials from your resource. In the sample below you'll use a Form Recognizer API key credential by creating an AzureKeyCredential object, that if needed, will allow you to update the API key without creating a new client.

You can set endpoint and apiKey based on an environment variable, a configuration setting, or any way that works for your application.

string endpoint = "<endpoint>";
string apiKey = "<apiKey>";
var credential = new AzureKeyCredential(apiKey);
var client = new DocumentAnalysisClient(new Uri(endpoint), credential);

Extract the layout of a document from a URI

To extract the layout from a given file at a URI, use the AnalyzeDocumentFromUri method and pass prebuilt-layout as the model ID. The returned value is an AnalyzeResult object containing data about the submitted document.

Uri fileUri = new Uri("<fileUri>");

AnalyzeDocumentOperation operation = await client.AnalyzeDocumentFromUriAsync(WaitUntil.Completed, "prebuilt-layout", fileUri);
AnalyzeResult result = operation.Value;

foreach (DocumentPage page in result.Pages)
{
    Console.WriteLine($"Document Page {page.PageNumber} has {page.Lines.Count} line(s), {page.Words.Count} word(s),");
    Console.WriteLine($"and {page.SelectionMarks.Count} selection mark(s).");

    for (int i = 0; i < page.Lines.Count; i++)
    {
        DocumentLine line = page.Lines[i];
        Console.WriteLine($"  Line {i} has content: '{line.Content}'.");

        Console.WriteLine($"    Its bounding polygon (points ordered clockwise):");

        for (int j = 0; j < line.BoundingPolygon.Count; j++)
        {
            Console.WriteLine($"      Point {j} => X: {line.BoundingPolygon[j].X}, Y: {line.BoundingPolygon[j].Y}");
        }
    }

    for (int i = 0; i < page.SelectionMarks.Count; i++)
    {
        DocumentSelectionMark selectionMark = page.SelectionMarks[i];

        Console.WriteLine($"  Selection Mark {i} is {selectionMark.State}.");
        Console.WriteLine($"    Its bounding polygon (points ordered clockwise):");

        for (int j = 0; j < selectionMark.BoundingPolygon.Count; j++)
        {
            Console.WriteLine($"      Point {j} => X: {selectionMark.BoundingPolygon[j].X}, Y: {selectionMark.BoundingPolygon[j].Y}");
        }
    }
}

Console.WriteLine("Paragraphs:");

foreach (DocumentParagraph paragraph in result.Paragraphs)
{
    Console.WriteLine($"  Paragraph content: {paragraph.Content}");

    if (paragraph.Role != null)
    {
        Console.WriteLine($"    Role: {paragraph.Role}");
    }
}

foreach (DocumentStyle style in result.Styles)
{
    // Check the style and style confidence to see if text is handwritten.
    // Note that value '0.8' is used as an example.

    bool isHandwritten = style.IsHandwritten.HasValue && style.IsHandwritten == true;

    if (isHandwritten && style.Confidence > 0.8)
    {
        Console.WriteLine($"Handwritten content found:");

        foreach (DocumentSpan span in style.Spans)
        {
            Console.WriteLine($"  Content: {result.Content.Substring(span.Index, span.Length)}");
        }
    }
}

Console.WriteLine("The following tables were extracted:");

for (int i = 0; i < result.Tables.Count; i++)
{
    DocumentTable table = result.Tables[i];
    Console.WriteLine($"  Table {i} has {table.RowCount} rows and {table.ColumnCount} columns.");

    foreach (DocumentTableCell cell in table.Cells)
    {
        Console.WriteLine($"    Cell ({cell.RowIndex}, {cell.ColumnIndex}) has kind '{cell.Kind}' and content: '{cell.Content}'.");
    }
}

Extract the layout of a document from a file stream

To extract the layout from a given file at a file stream, use the AnalyzeDocument method and pass prebuilt-layout as the model ID. The returned value is an AnalyzeResult object containing data about the submitted document.

string filePath = "<filePath>";
using var stream = new FileStream(filePath, FileMode.Open);

AnalyzeDocumentOperation operation = await client.AnalyzeDocumentAsync(WaitUntil.Completed, "prebuilt-layout", stream);
AnalyzeResult result = operation.Value;

foreach (DocumentPage page in result.Pages)
{
    Console.WriteLine($"Document Page {page.PageNumber} has {page.Lines.Count} line(s), {page.Words.Count} word(s),");
    Console.WriteLine($"and {page.SelectionMarks.Count} selection mark(s).");

    for (int i = 0; i < page.Lines.Count; i++)
    {
        DocumentLine line = page.Lines[i];
        Console.WriteLine($"  Line {i} has content: '{line.Content}'.");

        Console.WriteLine($"    Its bounding polygon (points ordered clockwise):");

        for (int j = 0; j < line.BoundingPolygon.Count; j++)
        {
            Console.WriteLine($"      Point {j} => X: {line.BoundingPolygon[j].X}, Y: {line.BoundingPolygon[j].Y}");
        }
    }

    for (int i = 0; i < page.SelectionMarks.Count; i++)
    {
        DocumentSelectionMark selectionMark = page.SelectionMarks[i];

        Console.WriteLine($"  Selection Mark {i} is {selectionMark.State}.");
        Console.WriteLine($"    Its bounding polygon (points ordered clockwise):");

        for (int j = 0; j < selectionMark.BoundingPolygon.Count; j++)
        {
            Console.WriteLine($"      Point {j} => X: {selectionMark.BoundingPolygon[j].X}, Y: {selectionMark.BoundingPolygon[j].Y}");
        }
    }
}

Console.WriteLine("Paragraphs:");

foreach (DocumentParagraph paragraph in result.Paragraphs)
{
    Console.WriteLine($"  Paragraph content: {paragraph.Content}");

    if (paragraph.Role != null)
    {
        Console.WriteLine($"    Role: {paragraph.Role}");
    }
}

foreach (DocumentStyle style in result.Styles)
{
    // Check the style and style confidence to see if text is handwritten.
    // Note that value '0.8' is used as an example.

    bool isHandwritten = style.IsHandwritten.HasValue && style.IsHandwritten == true;

    if (isHandwritten && style.Confidence > 0.8)
    {
        Console.WriteLine($"Handwritten content found:");

        foreach (DocumentSpan span in style.Spans)
        {
            Console.WriteLine($"  Content: {result.Content.Substring(span.Index, span.Length)}");
        }
    }
}

Console.WriteLine("The following tables were extracted:");

for (int i = 0; i < result.Tables.Count; i++)
{
    DocumentTable table = result.Tables[i];
    Console.WriteLine($"  Table {i} has {table.RowCount} rows and {table.ColumnCount} columns.");

    foreach (DocumentTableCell cell in table.Cells)
    {
        Console.WriteLine($"    Cell ({cell.RowIndex}, {cell.ColumnIndex}) has kind '{cell.Kind}' and content: '{cell.Content}'.");
    }
}