17 Unicode – a brief introduction (advanced)

Unicode is a standard for representing and managing text in most of the world’s writing systems. Virtually all modern software that works with text, supports Unicode. The standard is maintained by the Unicode Consortium. A new version of the standard is published every year (with new Emojis etc.). Unicode version 1.0.0 was published in October 1991.

17.1 Code points vs. code units

Two concepts are crucial for understanding Unicode:

• Code points are numbers that represent Unicode characters.
• Code units are numbers that encode code points, to store or transmit Unicode text. One or more code units encode a single code point. Each code unit has the same size, which depends on the encoding format that is used. The most popular format, UTF-8, has 8-bit code units.

17.1.1 Code points

The first version of Unicode had 16-bit code points. Since then, the number of characters has grown considerably and the size of code points was extended to 21 bits. These 21 bits are partitioned in 17 planes, with 16 bits each:

• Plane 0: Basic Multilingual Plane (BMP), 0x0000–0xFFFF
  • Contains characters for almost all modern languages (Latin characters, Asian characters, etc.) and many symbols.
• Plane 1: Supplementary Multilingual Plane (SMP), 0x10000–0x1FFFF
  • Supports historic writing systems (e.g. Egyptian hieroglyphs and cuneiform) and additional modern writing systems.
  • Supports emoji and many other symbols.
• Plane 2: Supplementary Ideographic Plane (SIP), 0x20000–0x2FFFF
  • Contains additional CJK (Chinese, Japanese, Korean) ideographs.
• Plane 3–13: Unassigned
• Plane 14: Supplementary Special-Purpose Plane (SSP), 0xE0000–0xEFFFF
  • Contains non-graphical characters such as tag characters and glyph variation selectors.
• Plane 15–16: Supplementary Private Use Area (S PUA A/B), 0x0F0000–0x10FFFF
  • Available for character assignment by parties outside the ISO and the Unicode Consortium. Not standardized.

Planes 1-16 are called supplementary planes or astral planes.

Let’s check the code points of a few characters:

> 'A'.codePointAt(0).toString(16)
'41'
> 'ü'.codePointAt(0).toString(16)
'fc'
> 'π'.codePointAt(0).toString(16)
'3c0'
> '🙂'.codePointAt(0).toString(16)
'1f642'

The hexadecimal numbers of the code points tell us that the first three characters reside in plane 0 (within 16 bits), while the emoji resides in plane 1.

17.1.2 Encoding Unicode code points: UTF-32, UTF-16, UTF-8

The main ways of encoding code points are three Unicode Transformation Formats (UTFs): UTF-32, UTF-16, UTF-8. The number at the end of each format indicates the size (in bits) of its code units.

17.1.2.1 UTF-32 (Unicode Transformation Format 32)

UTF-32 uses 32 bits to store code units, resulting in one code unit per code point. This format is the only one with fixed-length encoding; all others use a varying number of code units to encode a single code point.

17.1.2.2 UTF-16 (Unicode Transformation Format 16)

UTF-16 uses 16-bit code units. It encodes code points as follows:

• BMP (first 16 bits of Unicode): are stored in single code units.

• Astral planes: The BMP comprises 0x10_000 code points. Given that Unicode has a total of 0x110_000 code points, we still need to encode the remaining 0x100_000 code points (20 bits). The BMP has two ranges of unassigned code points that provide the necessary storage:

  • Most significant 10 bits (leading surrogate): 0xD800-0xDBFF
  • Least significant 10 bits (trailing surrogate): 0xDC00-0xDFFF

In other words: The two hexadecimal digits at the end contribute 8 bits. But we can only use those 8 bits if a BMP starts with one of the following 2-digit pairs:

• D8, D9, DA, DB
• DC, DD, DE, DF

Per surrogate, we have a choice between 4 pairs, which is where the remaining 2 bits come from.

As a consequence, each UTF-16 code unit is always either a leading surrogate, a trailing surrogate or encodes a BMP code point.

These are two examples of UTF-16-encoded code points:

• Code point 0x03C0 (π) is in the BMP and can therefore be represented by a single UTF-16 code unit: 0x03C0.
• Code point 0x1F642 (🙂) is in an astral plane and represented by two code units: 0xD83D and 0xDE42.

17.1.2.3 UTF-8 (Unicode Transformation Format 8)

UTF-8 has 8-bit code units. It uses 1–4 code units to encode a code point:

Notes:

• The bit prefix of each code unit tells us:
  • Is it first in a series of code units? If yes, how many code units will follow?
  • Is it second or later in a series of code units?
• The character mappings in the 0000–007F range are the same as ASCII, which leads to a degree of backward-compatibility with older software.

Three examples:

17.2 Encodings used in web development: UTF-16 and UTF-8

The Unicode encoding formats, that are used in web development, are: UTF-16 and UTF-8.

17.2.1 Source code internally: UTF-16

The ECMAScript specification internally represents source code as UTF-16.

17.2.2 Strings: UTF-16

The characters in JavaScript strings are based on UTF-16 code units:

> const smiley = '🙂';
> smiley.length
2
> smiley === '\uD83D\uDE42' // code units
true

For more information on Unicode and strings, consult §18.6 “Atoms of text: Unicode characters, JavaScript characters, grapheme clusters”.

17.2.3 Source code in files: UTF-8

HTML and JavaScript are almost always encoded as UTF-8, these days.

For example, this is how HTML files usually start now:

<!doctype html>
<html>
<head>
  <meta charset="UTF-8">
···

For HTML modules loaded in web browsers, the standard encoding is also UTF-8.

17.3 Grapheme clusters – the real characters

The concept of a character becomes remarkably complex, once you consider many of the world’s writing systems.

On one hand, there are Unicode characters, as represented by code points.

On the other hand, there are grapheme clusters. A grapheme cluster corresponds most closely to a symbol displayed on screen or paper. It is defined as “a horizontally segmentable unit of text”. Therefore, official Unicode documents also call it a user-perceived character. One or more code point characters are needed to encode a grapheme cluster.

For example, the Devanagari kshi is encoded by 4 code points. We use spreading (...) to split a string into an Array with code point characters (for details, consult §18.6.1 “Working with code points”):

Flag emojis are also grapheme clusters and composed of two code point characters. For example, the flag of Japan: