2022-07-18 23:30:32 +00:00
|
|
|
|
# go-utf8
|
2018-07-02 06:04:04 +00:00
|
|
|
|
|
2022-07-19 04:19:50 +00:00
|
|
|
|
Package **utf8** implements encoding and decoding of UTF-8, for the Go programming language.
|
2018-07-02 06:04:04 +00:00
|
|
|
|
|
2022-07-19 04:19:50 +00:00
|
|
|
|
This package is meant to be a replacement for Go's built-in `"unicode/utf8"` package.
|
2018-07-02 06:04:04 +00:00
|
|
|
|
|
|
|
|
|
## Documention
|
|
|
|
|
|
2023-08-16 12:23:58 +00:00
|
|
|
|
Online documentation, which includes examples, can be found at: http://godoc.org/sourcecode.social/reiver/go-utf8
|
2018-07-02 06:04:04 +00:00
|
|
|
|
|
2023-08-16 12:23:58 +00:00
|
|
|
|
[![GoDoc](https://godoc.org/sourcecode.social/reiver/go-utf8?status.svg)](https://godoc.org/sourcecode.social/reiver/go-utf8)
|
2018-07-02 06:04:04 +00:00
|
|
|
|
|
2022-07-19 04:19:50 +00:00
|
|
|
|
## Reading a Single UTF-8 Character
|
2018-07-02 06:04:04 +00:00
|
|
|
|
|
2022-07-19 04:19:50 +00:00
|
|
|
|
This is the simplest way of reading a single UTF-8 character.
|
2018-07-02 06:04:04 +00:00
|
|
|
|
|
|
|
|
|
```go
|
|
|
|
|
var reader io.Reader
|
|
|
|
|
|
|
|
|
|
// ...
|
|
|
|
|
|
2022-07-18 23:36:02 +00:00
|
|
|
|
r, n, err := utf8.ReadRune(reader)
|
2018-07-02 06:04:04 +00:00
|
|
|
|
```
|
2022-07-19 04:19:50 +00:00
|
|
|
|
## Write a Single UTF-8 Character
|
|
|
|
|
|
|
|
|
|
This is the simplest way of writing a single UTF-8 character.
|
2018-07-02 06:04:04 +00:00
|
|
|
|
|
|
|
|
|
```go
|
|
|
|
|
var writer io.Writer
|
|
|
|
|
|
|
|
|
|
// ...
|
|
|
|
|
|
|
|
|
|
var r rune
|
|
|
|
|
|
|
|
|
|
// ...
|
|
|
|
|
|
2022-07-18 23:36:02 +00:00
|
|
|
|
n, err := utf8.WriteRune(w, r)
|
2018-07-02 06:04:04 +00:00
|
|
|
|
```
|
2022-07-19 04:19:50 +00:00
|
|
|
|
## io.RuneReader
|
|
|
|
|
|
|
|
|
|
This is how you can create an `io.RuneReader`:
|
2018-07-11 03:43:45 +00:00
|
|
|
|
|
|
|
|
|
```go
|
|
|
|
|
var reader io.Reader
|
|
|
|
|
|
|
|
|
|
// ...
|
|
|
|
|
|
2022-07-19 04:19:50 +00:00
|
|
|
|
var runeReader io.RuneReader = utf8.RuneReaderWrap(reader)
|
2018-07-11 03:43:45 +00:00
|
|
|
|
|
|
|
|
|
// ...
|
|
|
|
|
|
|
|
|
|
r, n, err := runeReader.ReadRune()
|
|
|
|
|
```
|
2022-07-19 04:19:50 +00:00
|
|
|
|
## io.RuneScanner
|
|
|
|
|
|
|
|
|
|
This is how you can create an `io.RuneScanner`:
|
2018-07-11 04:01:30 +00:00
|
|
|
|
|
|
|
|
|
```go
|
|
|
|
|
var reader io.Reader
|
|
|
|
|
|
|
|
|
|
// ...
|
|
|
|
|
|
2022-07-19 04:19:50 +00:00
|
|
|
|
var runeScanner io.RuneScanner := utf8.RuneScannerWrap(reader)
|
2018-07-11 04:01:30 +00:00
|
|
|
|
|
|
|
|
|
// ...
|
|
|
|
|
|
|
|
|
|
r, n, err := runeScanner.ReadRune()
|
|
|
|
|
|
|
|
|
|
// ...
|
|
|
|
|
|
|
|
|
|
err = runeScanner.UnreadRune()
|
|
|
|
|
```
|
2022-07-19 04:19:50 +00:00
|
|
|
|
|
|
|
|
|
## UTF-8
|
|
|
|
|
|
|
|
|
|
UTF-8 is a variable length encoding of Unicode.
|
|
|
|
|
An encoding of a single Unicode code point can be from 1 to 4 bytes longs.
|
|
|
|
|
|
|
|
|
|
Some examples of UTF-8 encoding of Unicode code points are:
|
|
|
|
|
|
|
|
|
|
```
|
|
|
|
|
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━┳━━━━━━━━━━━━┳━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┓
|
|
|
|
|
┃ UTF-8 encoding ┃ ┃ ┃ ┃ ┃ ┃
|
|
|
|
|
┣━━━━━━━━━━━━━┳━━━━━━━━━━━━━┳━━━━━━━━━━━━━┳━━━━━━━━━━━━━┫ ┃ ┃ ┃ ┃ ┃
|
|
|
|
|
┃ byte 1 ┋ byte 2 ┋ byte 3 ┋ byte 4 ┃ value ┃ code point ┃ decimal ┃ binary ┃ name ┃
|
|
|
|
|
┡━━━━━━━━━━━━━╇━━━━━━━━━━━━━╇━━━━━━━━━━━━━╇━━━━━━━━━━━━━╇━━━━━━━╇━━━━━━━━━━━━╇━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┩
|
|
|
|
|
│ 0b0,1000001 ┊ ┊ ┊ │ A │ U+0041 │ 65 │ 0b0000,0000,0100,0001 │ LATIN CAPITAL LETTER A │
|
|
|
|
|
├─────────────┼─────────────┼─────────────┼─────────────┼───────┼────────────┼─────────┼────────────────────────────┼──────────────────────────────────┤
|
|
|
|
|
│ 0b0,1110010 ┊ ┊ ┊ │ r │ U+0072 │ 114 │ 0b0000,0000,0111,0010 │ LATIN SMALL LETTER R │
|
|
|
|
|
├─────────────┼─────────────┼─────────────┼─────────────┼───────┼────────────┼─────────┼────────────────────────────┼──────────────────────────────────┤
|
|
|
|
|
│ 0b110,00010 ┊ 0b10,100001 ┊ ┊ │ ¡ │ U+00A1 │ 161 │ 0b0000,0000,1010,0001 │ INVERTED EXCLAMATION MARK │
|
|
|
|
|
├─────────────┼─────────────┼─────────────┼─────────────┼───────┼────────────┼─────────┼────────────────────────────┼──────────────────────────────────┤
|
|
|
|
|
│ 0b110,11011 ┊ 0b10,110101 ┊ ┊ │ ۵ │ U+06F5 │ 1781 │ 0b0000,0110,1111,0101 │ EXTENDED ARABIC-INDIC DIGIT FIVE │
|
|
|
|
|
├─────────────┼─────────────┼─────────────┼─────────────┼───────┼────────────┼─────────┼────────────────────────────┼──────────────────────────────────┤
|
|
|
|
|
│ 0b1110,0010 ┊ 0b10,000000 ┊ 0b10,110001 ┊ │ ‱ │ U+2031 │ 8241 │ 0b0010,0000,0011,0001 │ PER TEN THOUSAND SIGN │
|
|
|
|
|
├─────────────┼─────────────┼─────────────┼─────────────┼───────┼────────────┼─────────┼────────────────────────────┼──────────────────────────────────┤
|
|
|
|
|
│ 0b1110,0010 ┊ 0b10,001001 ┊ 0b10,100001 ┊ │ ≡ │ U+2261 │ 8801 │ 0b0010,0010,0110,0001 │ IDENTICAL TO │
|
|
|
|
|
├─────────────┼─────────────┼─────────────┼─────────────┼───────┼────────────┼─────────┼────────────────────────────┼──────────────────────────────────┤
|
|
|
|
|
│ 0b11110,000 ┊ 0b10,010000 ┊ 0b10,001111 ┊ 0b10,010101 │ 𐏕 │ U+000103D5 │ 66517 │ 0b0001,0000,0011,1101,0101 │ OLD PERSIAN NUMBER HUNDRED │
|
|
|
|
|
├─────────────┼─────────────┼─────────────┼─────────────┼───────┼────────────┼─────────┼────────────────────────────┼──────────────────────────────────┤
|
|
|
|
|
│ 0b11110,000 ┊ 0b10,011111 ┊ 0b10,011001 ┊ 0b10,000010 │ 🙂 │ U+0001F642 │ 128578 │ 0b0001,1111,0110,0100,0010 │ SLIGHTLY SMILING FACE │
|
|
|
|
|
└─────────────┴─────────────┴─────────────┴─────────────┴───────┴────────────┴─────────┴────────────────────────────┴──────────────────────────────────┘
|
|
|
|
|
```
|
|
|
|
|
|
|
|
|
|
## UTF-8 Versus ASCII
|
|
|
|
|
|
|
|
|
|
UTF-8 was (partially) designed to be backwards compatible with 7-bit ASCII.
|
|
|
|
|
|
|
|
|
|
Thus, all 7-bit ASCII is valid UTF-8.
|
|
|
|
|
|
|
|
|
|
## UTF-8 Encoding
|
|
|
|
|
|
|
|
|
|
Since, at least as of 2003, Unicode fits into 21 bits, and thus UTF-8 was designed to support at most 21 bits of information.
|
|
|
|
|
|
|
|
|
|
This is done as described in the following table:
|
|
|
|
|
|
|
|
|
|
```
|
|
|
|
|
┏━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━┳━━━━━━━━━━┳━━━━━━━━━━┳━━━━━━━━━━┓
|
|
|
|
|
┃ # of bytes ┃ # bits for code point ┃ 1st code point ┃ last code point ┃ byte 1 ┃ byte 2 ┃ byte 3 ┃ byte 4 ┃
|
|
|
|
|
┡━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━╇━━━━━━━━━━╇━━━━━━━━━━╇━━━━━━━━━━┩
|
|
|
|
|
│ 1 │ 7 │ U+000000 │ U+00007F │ 0xxxxxxx │ │ │ │
|
|
|
|
|
├────────────┼───────────────────────┼────────────────┼──────────────────┼──────────┼──────────┼──────────┼──────────┤
|
|
|
|
|
│ 2 │ 11 │ U+000080 │ U+0007FF │ 110xxxxx │ 10xxxxxx │ │ │
|
|
|
|
|
├────────────┼───────────────────────┼────────────────┼──────────────────┼──────────┼──────────┼──────────┼──────────┤
|
|
|
|
|
│ 3 │ 16 │ U+000800 │ U+00FFFF │ 1110xxxx │ 10xxxxxx │ 10xxxxxx │ │
|
|
|
|
|
├────────────┼───────────────────────┼────────────────┼──────────────────┼──────────┼──────────┼──────────┼──────────┤
|
|
|
|
|
│ 4 │ 21 │ U+010000 │ U+10FFFF │ 11110xxx │ 10xxxxxx │ 10xxxxxx │ 10xxxxxx │
|
|
|
|
|
└────────────┴───────────────────────┴────────────────┴──────────────────┴──────────┴──────────┴──────────┴──────────┘
|
|
|
|
|
```
|