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
|
const std = @import("std");
const builtin = @import("builtin");
pub fn main() anyerror!void {
var arena = std.heap.ArenaAllocator.init(std.heap.page_allocator);
defer arena.deinit();
const allocator = arena.allocator();
var write_buf: [4096]u8 = undefined;
// Process UnicodeData.txt
var in_reader = std.io.Reader.fixed(@embedFile("UnicodeData.txt"));
var args_iter = try std.process.argsWithAllocator(allocator);
defer args_iter.deinit();
_ = args_iter.skip();
const output_path = args_iter.next() orelse @panic("No output file arg!");
var out_file = try std.fs.cwd().createFile(output_path, .{});
defer out_file.close();
var file_writer = out_file.writer(&write_buf);
var writer = &file_writer.interface;
const endian = builtin.cpu.arch.endian();
lines: while (in_reader.takeDelimiterInclusive('\n')) |took| {
const line = std.mem.trimRight(u8, took, "\n");
if (line.len == 0) continue;
var field_iter = std.mem.splitScalar(u8, line, ';');
var cps: [3]u24 = undefined;
var len: u8 = 2;
var i: usize = 0;
while (field_iter.next()) |field| : (i += 1) {
switch (i) {
0 => cps[0] = try std.fmt.parseInt(u24, field, 16),
5 => {
// Not canonical.
if (field.len == 0 or field[0] == '<') continue :lines;
if (std.mem.indexOfScalar(u8, field, ' ')) |space| {
// Canonical
len = 3;
cps[1] = try std.fmt.parseInt(u24, field[0..space], 16);
cps[2] = try std.fmt.parseInt(u24, field[space + 1 ..], 16);
} else {
// Singleton
cps[1] = try std.fmt.parseInt(u24, field, 16);
}
},
2 => if (line[0] == '<') continue :lines,
else => {},
}
}
try writer.writeInt(u8, @intCast(len), endian);
for (cps[0..len]) |cp| try writer.writeInt(u24, cp, endian);
} else |err| switch (err) {
error.EndOfStream => {},
else => {
return err;
},
}
try writer.writeInt(u16, 0, endian);
try writer.flush();
}
|
