Get All Available Characters from a Font

Get all available characters from a font

For each UIFont, you have to get characterSet of that font. For example, I take first UIFont.

let firsttFont = UIFont.familyNames.first

let first = UIFont(name: firsttFont!, size: 14)
let fontDescriptor = first!.fontDescriptor
let characterSet : NSCharacterSet = fontDescriptor.object(forKey: UIFontDescriptorCharacterSetAttribute) as! NSCharacterSet

Then, use this extension to get all characters of that NSCharacterSet:

extension NSCharacterSet {
    var characters:[String] {
        var chars = [String]()
        for plane:UInt8 in 0...16 {
            if self.hasMemberInPlane(plane) {
                let p0 = UInt32(plane) << 16
                let p1 = (UInt32(plane) + 1) << 16
                for c:UTF32Char in p0..<p1 {
                    if self.longCharacterIsMember(c) {
                        var c1 = c.littleEndian
                        let s = NSString(bytes: &c1, length: 4, encoding: String.Encoding.utf32LittleEndian.rawValue)!
                        chars.append(String(s))
                    }
                }
            }
        }
        return chars
    }
}

(Ref: NSArray from NSCharacterset)

So, at last, just call characterSet.characters to get all characters (in String)

How to get all characters of the font with CTFontCopyCharacterSet() in Swift?

CFCharacterSet is toll-free bridged with the Cocoa Foundation counterpart NSCharacterSet, and can be bridged to the corresponding Swift value type CharacterSet:

let charset = CTFontCopyCharacterSet(ctFont) as CharacterSet

Then the approach from NSArray from NSCharacterSet can be used to enumerate all Unicode scalar values of that character set (including non-BMP points, i.e. Unicode scalar values greater than U+FFFF).

The CTFontGetGlyphsForCharacters() expects non-BMP characters as surrogate pair, i.e. as an array of UTF-16 code units.

Putting it together, the function would look like this:

func createUnicodeFontMap(ctFont: CTFont) ->  [CGGlyph : UnicodeScalar] {

    let charset = CTFontCopyCharacterSet(ctFont) as CharacterSet

    var glyphToUnicode = [CGGlyph : UnicodeScalar]() // Start with empty map.

    // Enumerate all Unicode scalar values from the character set:
    for plane: UInt8 in 0...16 where charset.hasMember(inPlane: plane) {
        for unicode in UTF32Char(plane) << 16 ..< UTF32Char(plane + 1) << 16 {
            if let uniChar = UnicodeScalar(unicode), charset.contains(uniChar) {

                // Get glyph for this `uniChar` ...
                let utf16 = Array(uniChar.utf16)
                var glyphs = [CGGlyph](repeating: 0, count: utf16.count)
                if CTFontGetGlyphsForCharacters(ctFont, utf16, &glyphs, utf16.count) {
                    // ... and add it to the map.
                    glyphToUnicode[glyphs[0]] = uniChar
                }
            }
        }
    }

    return glyphToUnicode
}

Finding out what characters a given font supports

Here is a method using the fontTools Python library (which you can install with something like pip install fonttools):

#!/usr/bin/env python
from itertools import chain
import sys

from fontTools.ttLib import TTFont
from fontTools.unicode import Unicode

with TTFont(
    sys.argv[1], 0, allowVID=0, ignoreDecompileErrors=True, fontNumber=-1
) as ttf:
    chars = chain.from_iterable(
        [y + (Unicode[y[0]],) for y in x.cmap.items()] for x in ttf["cmap"].tables
    )
    if len(sys.argv) == 2:  # print all code points
        for c in chars:
            print(c)
    elif len(sys.argv) >= 3:  # search code points / characters
        code_points = {c[0] for c in chars}
        for i in sys.argv[2:]:
            code_point = int(i)   # search code point
            #code_point = ord(i)  # search character
            print(Unicode[code_point])
            print(code_point in code_points)

The script takes as arguments the font path and optionally code points / characters to search for:

$ python checkfont.py /usr/share/fonts/**/DejaVuSans.ttf
(32, 'space', 'SPACE')
(33, 'exclam', 'EXCLAMATION MARK')
(34, 'quotedbl', 'QUOTATION MARK')
…

$ python checkfont.py /usr/share/fonts/**/DejaVuSans.ttf 65 12622  # a ㅎ
LATIN CAPITAL LETTER A
True
HANGUL LETTER HIEUH
False

c# get all characters of a font as array or list

Please check the following code by Jawahar Suresh Babu in CodeProject. I believe it does what you want.

Character Map in WPF

http://www.codeproject.com/Articles/396811/Character-Map-in-WPF

To get the character escaped code, you can change the Select event handler method in the code above as follows:

    private void Select(object sender, RoutedEventArgs e)
    {
        if (currentindex != -1)
        {
            text.BeginChange();
            if (text.Selection.Text != string.Empty)
            {
                text.Selection.Text = string.Empty;
            }

            var ch = new Run(((SymbolView) canvas.Children[currentindex]).charcter.Text)
                {
                    FontFamily = fonts.SelectedItem as FontFamily
                };

            text.CaretPosition.Paragraph.Inlines.Add(ch);

            text.EndChange();

            // Displays escaped char code
            MessageBox.Show(string.Format("&#x{0:X4}", (int) ch.Text[0])); 
        }
    }

EDIT: Included change to get the character escaped code.

---

Related Topics