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
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
|
const std = @import("std");
const fmt = std.fmt;
const fs = std.fs;
const io = std.io;
const heap = std.heap;
const mem = std.mem;
const testing = std.testing;
const unicode = std.unicode;
const grapheme = @import("Graphemes");
const Grapheme = @import("Graphemes").Grapheme;
const Graphemes = @import("Graphemes");
const GraphemeIterator = @import("Graphemes").Iterator;
const Normalize = @import("Normalize");
comptime {
testing.refAllDecls(grapheme);
}
test "Iterator.peek" {
const peek_seq = "aΔ👨🏻🌾→";
const data = try Graphemes.init(std.testing.allocator);
defer data.deinit(std.testing.allocator);
var iter = data.iterator(peek_seq);
const peek_a = iter.peek().?;
const next_a = iter.next().?;
try std.testing.expectEqual(peek_a, next_a);
try std.testing.expectEqualStrings("a", peek_a.bytes(peek_seq));
const peek_d1 = iter.peek().?;
const peek_d2 = iter.peek().?;
try std.testing.expectEqual(peek_d1, peek_d2);
const next_d = iter.next().?;
try std.testing.expectEqual(peek_d2, next_d);
try std.testing.expectEqual(iter.peek(), iter.next());
try std.testing.expectEqual(iter.peek(), iter.next());
try std.testing.expectEqual(null, iter.peek());
try std.testing.expectEqual(null, iter.peek());
try std.testing.expectEqual(iter.peek(), iter.next());
}
test "Unicode normalization tests" {
var arena = heap.ArenaAllocator.init(testing.allocator);
defer arena.deinit();
var allocator = arena.allocator();
const n = try Normalize.init(allocator);
defer n.deinit(allocator);
var file = try fs.cwd().openFile("data/unicode/NormalizationTest.txt", .{});
defer file.close();
var buf_reader = io.bufferedReader(file.reader());
const input_stream = buf_reader.reader();
var line_no: usize = 0;
var buf: [4096]u8 = undefined;
var cp_buf: [4]u8 = undefined;
while (try input_stream.readUntilDelimiterOrEof(&buf, '\n')) |line| {
line_no += 1;
// Skip comments or empty lines.
if (line.len == 0 or line[0] == '#' or line[0] == '@') continue;
// Iterate over fields.
var fields = mem.splitScalar(u8, line, ';');
var field_index: usize = 0;
var input: []u8 = undefined;
defer allocator.free(input);
while (fields.next()) |field| : (field_index += 1) {
if (field_index == 0) {
var i_buf = std.ArrayList(u8).init(allocator);
defer i_buf.deinit();
var i_fields = mem.splitScalar(u8, field, ' ');
while (i_fields.next()) |s| {
const icp = try fmt.parseInt(u21, s, 16);
const len = try unicode.utf8Encode(icp, &cp_buf);
try i_buf.appendSlice(cp_buf[0..len]);
}
input = try i_buf.toOwnedSlice();
} else if (field_index == 1) {
//debug.print("\n*** {s} ***\n", .{line});
// NFC, time to test.
var w_buf = std.ArrayList(u8).init(allocator);
defer w_buf.deinit();
var w_fields = mem.splitScalar(u8, field, ' ');
while (w_fields.next()) |s| {
const wcp = try fmt.parseInt(u21, s, 16);
const len = try unicode.utf8Encode(wcp, &cp_buf);
try w_buf.appendSlice(cp_buf[0..len]);
}
const want = w_buf.items;
var got = try n.nfc(allocator, input);
defer got.deinit(allocator);
try testing.expectEqualStrings(want, got.slice);
} else if (field_index == 2) {
// NFD, time to test.
var w_buf = std.ArrayList(u8).init(allocator);
defer w_buf.deinit();
var w_fields = mem.splitScalar(u8, field, ' ');
while (w_fields.next()) |s| {
const wcp = try fmt.parseInt(u21, s, 16);
const len = try unicode.utf8Encode(wcp, &cp_buf);
try w_buf.appendSlice(cp_buf[0..len]);
}
const want = w_buf.items;
var got = try n.nfd(allocator, input);
defer got.deinit(allocator);
try testing.expectEqualStrings(want, got.slice);
} else if (field_index == 3) {
// NFKC, time to test.
var w_buf = std.ArrayList(u8).init(allocator);
defer w_buf.deinit();
var w_fields = mem.splitScalar(u8, field, ' ');
while (w_fields.next()) |s| {
const wcp = try fmt.parseInt(u21, s, 16);
const len = try unicode.utf8Encode(wcp, &cp_buf);
try w_buf.appendSlice(cp_buf[0..len]);
}
const want = w_buf.items;
var got = try n.nfkc(allocator, input);
defer got.deinit(allocator);
try testing.expectEqualStrings(want, got.slice);
} else if (field_index == 4) {
// NFKD, time to test.
var w_buf = std.ArrayList(u8).init(allocator);
defer w_buf.deinit();
var w_fields = mem.splitScalar(u8, field, ' ');
while (w_fields.next()) |s| {
const wcp = try fmt.parseInt(u21, s, 16);
const len = try unicode.utf8Encode(wcp, &cp_buf);
try w_buf.appendSlice(cp_buf[0..len]);
}
const want = w_buf.items;
const got = try n.nfkd(allocator, input);
defer got.deinit(allocator);
try testing.expectEqualStrings(want, got.slice);
} else {
continue;
}
}
}
}
test "Segmentation GraphemeIterator" {
const allocator = std.testing.allocator;
var file = try std.fs.cwd().openFile("data/unicode/auxiliary/GraphemeBreakTest.txt", .{});
defer file.close();
var buf_reader = std.io.bufferedReader(file.reader());
var input_stream = buf_reader.reader();
const data = try Graphemes.init(allocator);
defer data.deinit(allocator);
var buf: [4096]u8 = undefined;
var line_no: usize = 1;
while (try input_stream.readUntilDelimiterOrEof(&buf, '\n')) |raw| : (line_no += 1) {
// Skip comments or empty lines.
if (raw.len == 0 or raw[0] == '#' or raw[0] == '@') continue;
// Clean up.
var line = std.mem.trimLeft(u8, raw, "÷ ");
if (std.mem.indexOf(u8, line, " ÷\t#")) |octo| {
line = line[0..octo];
}
// Iterate over fields.
var want = std.ArrayList(Grapheme).init(allocator);
defer want.deinit();
var all_bytes = std.ArrayList(u8).init(allocator);
defer all_bytes.deinit();
var graphemes = std.mem.splitSequence(u8, line, " ÷ ");
var bytes_index: u32 = 0;
while (graphemes.next()) |field| {
var code_points = std.mem.splitScalar(u8, field, ' ');
var cp_buf: [4]u8 = undefined;
var cp_index: u32 = 0;
var gc_len: u8 = 0;
while (code_points.next()) |code_point| {
if (std.mem.eql(u8, code_point, "×")) continue;
const cp: u21 = try std.fmt.parseInt(u21, code_point, 16);
const len = try unicode.utf8Encode(cp, &cp_buf);
try all_bytes.appendSlice(cp_buf[0..len]);
cp_index += len;
gc_len += len;
}
try want.append(Grapheme{ .len = gc_len, .offset = bytes_index });
bytes_index += cp_index;
}
// std.debug.print("\nline {}: {s}\n", .{ line_no, all_bytes.items });
var iter = data.iterator(all_bytes.items);
// Check.
for (want.items) |want_gc| {
const got_gc = (iter.next()).?;
try std.testing.expectEqualStrings(
want_gc.bytes(all_bytes.items),
got_gc.bytes(all_bytes.items),
);
}
}
}
test "Segmentation ReverseGraphemeIterator" {
const allocator = std.testing.allocator;
var file = try std.fs.cwd().openFile("data/unicode/auxiliary/GraphemeBreakTest.txt", .{});
defer file.close();
var buf_reader = std.io.bufferedReader(file.reader());
var input_stream = buf_reader.reader();
const data = try Graphemes.init(allocator);
defer data.deinit(allocator);
var buf: [4096]u8 = undefined;
var line_no: usize = 1;
while (try input_stream.readUntilDelimiterOrEof(&buf, '\n')) |raw| : (line_no += 1) {
// Skip comments or empty lines.
if (raw.len == 0 or raw[0] == '#' or raw[0] == '@') continue;
// Clean up.
var line = std.mem.trimLeft(u8, raw, "÷ ");
if (std.mem.indexOf(u8, line, " ÷\t#")) |octo| {
line = line[0..octo];
}
// Iterate over fields.
var want = std.ArrayList(Grapheme).init(allocator);
defer want.deinit();
var all_bytes = std.ArrayList(u8).init(allocator);
defer all_bytes.deinit();
var graphemes = std.mem.splitSequence(u8, line, " ÷ ");
var bytes_index: u32 = 0;
while (graphemes.next()) |field| {
var code_points = std.mem.splitScalar(u8, field, ' ');
var cp_buf: [4]u8 = undefined;
var cp_index: u32 = 0;
var gc_len: u8 = 0;
while (code_points.next()) |code_point| {
if (std.mem.eql(u8, code_point, "×")) continue;
const cp: u21 = try std.fmt.parseInt(u21, code_point, 16);
const len = try unicode.utf8Encode(cp, &cp_buf);
try all_bytes.appendSlice(cp_buf[0..len]);
cp_index += len;
gc_len += len;
}
try want.append(Grapheme{ .len = gc_len, .offset = bytes_index });
bytes_index += cp_index;
}
// std.debug.print("\nline {}: {s}\n", .{ line_no, all_bytes.items });
var iter = data.reverseIterator(all_bytes.items);
// Check.
var i: usize = want.items.len;
while (i > 0) {
i -= 1;
const want_gc = want.items[i];
const got_gc = iter.prev() orelse {
std.debug.print("line {d} grapheme {d}: expected {any} found null\n", .{ line_no, i, want_gc });
return error.TestExpectedEqual;
};
std.testing.expectEqualStrings(
want_gc.bytes(all_bytes.items),
got_gc.bytes(all_bytes.items),
) catch |err| {
std.debug.print("line {d} grapheme {d}: expected {any} found {any}\n", .{ line_no, i, want_gc, got_gc });
return err;
};
}
}
}
|
