File: strings_test.ha

package info (click to toggle)
hare 0.26.0-1
  • links: PTS, VCS
  • area: main
  • in suites: forky, sid
  • size: 7,352 kB
  • sloc: asm: 1,374; makefile: 123; sh: 117; lisp: 101
file content (161 lines) | stat: -rw-r--r-- 5,028 bytes parent folder | download
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
// SPDX-License-Identifier: MPL-2.0
// (c) Hare authors <https://harelang.org>

use bytes;
use fmt;
use io;
use strings;


fn c_checkrange(chars: []u8, f: *fn (c: u8) bool) void = {
	for (let i = 0z; i < 256; i += 1) {
		let expected = for (let j = 0z; j < len(chars); j += 1) {
			if (chars[j] == i: u8) {
				break true;
			};
		} else false;

		if (f(i: u8) != expected) {
			fmt::println(i, expected, f(i: u8))!;
		};
		assert(f(i: u8) == expected);
	};
};

@test fn c_is_num() void = {
	const chars: [_]u8 = [
		'0', '1', '2', '3', '4', '5', '6', '7', '8', '9', ' ',
	];
	c_checkrange(chars, &c_is_num);
};

@test fn c_is_print() void = {
	const chars: [_]u8 = [
		'a', 'b', 'c', 'd', 'e', 'f', 'g', 'h', 'i', 'j', 'k', 'l', 'm',
		'n', 'o', 'p', 'q', 'r', 's', 't', 'u', 'v', 'w', 'x', 'y', 'z',
		'A', 'B', 'C', 'D', 'E', 'F', 'G', 'H', 'I', 'J', 'K', 'L', 'M',
		'N', 'O', 'P', 'Q', 'R', 'S', 'T', 'U', 'V', 'W', 'X', 'Y', 'Z',
		'0', '1', '2', '3', '4', '5', '6', '7', '8', '9', ' ', '\'',
		'(', ')', '+', ',', '-', '.', '/', ':', '=', '?',
	];
	c_checkrange(chars, &c_is_print);
};

@test fn utf8() void = {
	let buf: [16]u8 = [0...];
	let b: [_]u8 = [
		0x55,
		0x56,
		0xd0, 0x98,
		0xe0, 0xa4, 0xb9,
		0xf0, 0x90, 0x8d, 0x88
	];
	const runesat: [_]size = [0, 1, 2, 2, 4, 4, 4, 7, 7, 7, 7, 8];

	let expected: str = strings::fromutf8([0xf0, 0x90, 0x8d, 0x88])!;
	assert(read_utf8str(&d([0x0c, 0x04, 0xf0, 0x90, 0x8d, 0x88]), buf)!
		== expected);
	assert(read_utf8str(&d([0x0c, 0x03, 0xf0, 0x90, 0x8d]), buf) is invalid);

	bytes::zero(buf);
	let r = strreader(&d([0x0c, 0x04, 0xf0, 0x90, 0x8d, 0x88]), utag::UTF8_STRING)!;
	assert(io::read(&r, buf)! == 4);
	assert(bytes::equal(buf[..4], strings::toutf8(expected)));

	bytes::zero(buf);
	let expected: str = strings::fromutf8([0x55, 0x56, 0xf0, 0x90, 0x8d, 0x88])!;
	assert(read_utf8str(&d([0x0c, 0x06, 0x55, 0x56, 0xf0, 0x90, 0x8d, 0x88]), buf)!
		== expected);
	assert(read_utf8str(&d([0x0c, 0x05, 0x55, 0x56, 0xf0, 0x90, 0x8d]), buf) is invalid);

	bytes::zero(buf);
	let r = strreader(&d([0x0c, 0x06, 0x55, 0x56, 0xf0, 0x90, 0x8d, 0x88]), utag::UTF8_STRING)!;
	assert(io::read(&r, buf)! == 6);
	assert(bytes::equal(buf[..6], strings::toutf8(expected)));

	let r = strreader(&d([0x0c, 0x05, 0x55, 0x56, 0xf0, 0x90, 0x8d]), utag::UTF8_STRING)!;
	assert(unwrap_err(io::readall(&r, buf[2..]) as io::error) is invalid);

	bytes::zero(buf);
	let r = strreader(&d([0x0c, 0x06, 0x55, 0x56, 0xf0, 0x90, 0x8d, 0x88]), utag::UTF8_STRING)!;
	assert(io::read(&r, buf[..4])! == 2);
	assert(io::read(&r, buf[2..])! == 4);
	assert(bytes::equal(buf[..6], strings::toutf8(expected)));

	bytes::zero(buf);
	let r = strreader(&d([0x0c, 0x05, 0x55, 0x56, 0xf0, 0x90, 0x8d]), utag::UTF8_STRING)!;
	assert(io::read(&r, buf[..4])! == 2);
	assert(unwrap_err(io::readall(&r, buf[2..]) as io::error) is invalid);
};

@test fn t61() void = {
	let input: [_]u8 = [
		0x14, 0x29,
		0x42, 0xc8, 0x61, 0x72, 0x65, 0x6e, 0x20, 0x76, 0x65, 0x72,
		0x7a, 0x65, 0x68, 0x72, 0x65, 0x6e, 0x20, 0x67, 0x65, 0x72,
		0x6e, 0x65, 0x20, 0xc8, 0x75, 0x62, 0x65, 0x72, 0x6d, 0xc8,
		0x61, 0xfb, 0x69, 0x67, 0x20, 0x48, 0x6f, 0x6e, 0x69, 0x67,
		0x0a,
	];

	const expected: [_]u8 = [
		0x42, 0xc3, 0xa4, 0x72, 0x65, 0x6e, 0x20, 0x76, 0x65, 0x72,
		0x7a, 0x65, 0x68, 0x72, 0x65, 0x6e, 0x20, 0x67, 0x65, 0x72,
		0x6e, 0x65, 0x20, 0xc3, 0xbc, 0x62, 0x65, 0x72, 0x6d, 0xc3,
		0xa4, 0xc3, 0x9f, 0x69, 0x67, 0x20, 0x48, 0x6f, 0x6e, 0x69,
		0x67, 0x0a,
	];

	let dec = d(input);
	let r = strreader(&dec, utag::TELETEX_STRING)!;
	let result = io::drain(&r)!;
	defer free(result);
	assert(bytes::equal(expected, result));
	assert(trypeek(&dec) is io::EOF);

	// cut off multibyte char
	input[1] = 0x2;
	let r = strreader(&d(input[..4]), utag::TELETEX_STRING)!;
	assert(unwrap_err(io::drain(&r) as io::error) is invalid);

	// not enough space for multibyte char
	let buf: [24]u8 = [0...];
	let in = input[..27];
	in[1] = (len(in) - 2): u8;
	let dec = d(in);
	let r = strreader(&dec, utag::TELETEX_STRING)!;
	assert(io::read(&r, buf)! == 23);
	assert(trypeek(&dec) is badformat);

	let r = strreader(&d([
		0x14, 0x0f, 0x63, 0x6c, 0xc2, 0x65, 0x73, 0x20, 0x70, 0x75,
		0x62, 0x6c, 0x69, 0x71, 0x75, 0x65, 0x73,
	]), utag::TELETEX_STRING)!;
	let b = io::drain(&r)!;
	defer free(b);

	assert(strings::fromutf8(b)! == "cl\u00e9s publiques");
};

@test fn bmp() void = {
	let input: [_]u8 = [
		0x1e, 0x26,
		0x00, 0x48, 0x00, 0xe4, 0x00, 0x72, 0x00, 0x65, 0x00, 0x6c,
		0x00, 0x61, 0x00, 0x6e, 0x00, 0x67, 0x00, 0x20, 0x00, 0x69,
		0x01, 0x61, 0x00, 0x20, 0x00, 0x6e, 0x00, 0x65, 0x00, 0x61,
		0x00, 0x74, 0x00, 0x6f, 0x00, 0x20, 0x27, 0x64,
	];

	const expected: [_]u8 = [
		0x48, 0xc3, 0xa4, 0x72, 0x65, 0x6c, 0x61, 0x6e, 0x67, 0x20,
		0x69, 0xc5, 0xa1, 0x20, 0x6e, 0x65, 0x61, 0x74, 0x6f, 0x20,
		0xe2, 0x9d, 0xa4,
	];

	let dec = d(input);
	let r = strreader(&dec, utag::BMP_STRING)!;
	let result = io::drain(&r)!;
	defer free(result);
	assert(bytes::equal(expected, result));
	assert(trypeek(&dec) is io::EOF);
};