Struct TextSegment

Namespace

Egami.Fonts.Unicode

Assembly

Egami.Fonts.dll

A range of UTF-16 units: a grapheme cluster, a word or a run.

public readonly record struct TextSegment : IEquatable<TextSegment>

Implements

IEquatable<TextSegment>

Inherited Members

ValueType.Equals(object)

ValueType.GetHashCode()

ValueType.ToString()

object.Equals(object, object)

object.GetType()

object.ReferenceEquals(object, object)

Examples

// A family emoji is one grapheme cluster of eight UTF-16 units; "can't" is one word.
string text = "\uD83D\uDC68\u200D\uD83D\uDC69\u200D\uD83D\uDC67 can't stop";
var graphemes = new List<TextSegment>();
foreach (TextSegment grapheme in TextSegmenter.Graphemes(text))
{
    graphemes.Add(grapheme);
}

var words = new List<string>();
foreach (TextSegment word in TextSegmenter.Words(text))
{
    words.Add(text.Substring(word.Start, word.Length));
}

bool inside = TextSegmenter.IsGraphemeBoundary(text, 2); // false: inside the family

Constructors

TextSegment(int, int)

A range of UTF-16 units: a grapheme cluster, a word or a run.

public TextSegment(int Start, int Length)

Parameters

Start int

The index of the first UTF-16 unit.

Length int

The number of UTF-16 units.

Examples

// A family emoji is one grapheme cluster of eight UTF-16 units; "can't" is one word.
string text = "\uD83D\uDC68\u200D\uD83D\uDC69\u200D\uD83D\uDC67 can't stop";
var graphemes = new List<TextSegment>();
foreach (TextSegment grapheme in TextSegmenter.Graphemes(text))
{
    graphemes.Add(grapheme);
}

var words = new List<string>();
foreach (TextSegment word in TextSegmenter.Words(text))
{
    words.Add(text.Substring(word.Start, word.Length));
}

bool inside = TextSegmenter.IsGraphemeBoundary(text, 2); // false: inside the family

Properties

End

Gets the index just past the segment.

public int End { get; }

Property Value

int

Length

The number of UTF-16 units.

public int Length { get; init; }

Property Value

int

Start

The index of the first UTF-16 unit.

public int Start { get; init; }

Property Value

int