toybox/tests/unicode.test
Elliott Hughes ed3d5eb0ea unicode: new toy.
Based loosely on the Plan9/Inferno utility, and a convenient way to go back
and forth between code points and utf8 sequences.

This patch also fixes a couple of bugs in wctoutf8 (and the tests for this
toy effectively serve as unit tests for wctoutf8/utf8towc).
2020-12-06 02:24:12 -06:00

14 lines
696 B
Bash
Executable File
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

#!/bin/bash
[ -f testing.sh ] && . testing.sh
#testing "name" "command" "result" "infile" "stdin"
testing "text" "unicode 안녕 hi" "U+C548 : 안 : 0xec 0x95 0x88\nU+B155 : 녕 : 0xeb 0x85 0x95\nU+0068 : h\nU+0069 : i\n" "" ""
testing "code points" "unicode 70 666" "U+0070 : p\nU+0666 : ٦ : 0xd9 0xa6\n" "" ""
testing "ASCII controls" "unicode 0" "U+0000 : NUL\n" "" ""
testing "del" "unicode 7f" "U+007F : DEL\n" "" ""
testing "3-byte" "unicode 30b9" "U+30B9 : ス : 0xe3 0x82 0xb9\n" "" ""
testing "4-byte" "unicode 10000" "U+10000 : 𐀀 : 0xf0 0x90 0x80 0x80\n" "" ""
testing "range" "unicode 660-662" "U+0660 : ٠ : 0xd9 0xa0\nU+0661 : ١ : 0xd9 0xa1\nU+0662 : ٢ : 0xd9 0xa2\n" "" ""