rtoon 0.1.1

Token-Oriented Object Notation - A compact, human-readable format for LLM data with 30-60% fewer tokens than JSON
Documentation
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
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
use rtoon::{
    decode,
    decode_default,
    decode_strict,
    DecodeOptions,
    ToonError,
};
use serde_json::json;

#[test]
fn test_invalid_syntax_errors() {
    let cases = vec![
        ("items[]: a,b", "Expected array length"),
        ("items[2]{name: a,b", "Expected '}'"),
        ("key value", "Expected"),
    ];

    for (input, expected_msg) in cases {
        let result = decode_default(input);
        if result.is_err() {
            let err = result.unwrap_err();
            let err_str = err.to_string();
            assert!(
                err_str.contains(expected_msg)
                    || err_str.contains("Parse error")
                    || err_str.contains("Invalid"),
                "Expected error containing '{}' but got: {}",
                expected_msg,
                err_str
            );
        } else {
            if input == "key value" {
                assert!(result.is_ok(), "'key value' is valid as a root string");
            }
        }
    }

    let invalid_cases = vec![
        ("items[2: a,b", "Expected ']'"),
        ("items[abc]: 1,2", "Expected array length"),
    ];

    for (input, expected_msg) in invalid_cases {
        let result = decode_default(input);
        assert!(result.is_err(), "Expected error for input: {}", input);

        let err = result.unwrap_err();
        let err_str = err.to_string();
        assert!(
            err_str.contains(expected_msg) || err_str.contains("Parse error"),
            "Expected error containing '{}' but got: {}",
            expected_msg,
            err_str
        );
    }
}

#[test]
fn test_type_mismatch_errors() {
    let cases = vec![
        ("value: ", "Empty value"),
        ("items[abc]: 1,2", "Invalid array length"),
    ];

    for (input, description) in cases {
        let result = decode_default(input);
        println!("Test case '{}': {:?}", description, result);
    }
}

#[test]
fn test_length_mismatch_strict_mode() {
    let test_cases = vec![("items[3]: a,b", 3, 2), ("items[5]: x", 5, 1)];

    for (input, expected, actual) in test_cases {
        let result = decode_strict(input);

        assert!(
            result.is_err(),
            "Expected error for input '{}' (expected: {}, actual: {})",
            input,
            expected,
            actual
        );

        if let Err(ToonError::LengthMismatch {
            expected: exp,
            found: fnd,
            ..
        }) = result
        {
            assert_eq!(
                exp, expected,
                "Expected length {} but got {} for input '{}'",
                expected, exp, input
            );
            assert_eq!(
                fnd, actual,
                "Expected found {} but got {} for input '{}'",
                actual, fnd, input
            );
        }
    }

    let result = decode_strict("items[1]: a,b,c");

    match result {
        Ok(val) => {
            assert_eq!(val["items"], json!(["a"]));
        }
        Err(_) => {}
    }
}

#[test]
fn test_length_mismatch_non_strict_mode() {
    let test_cases = vec![
        ("items[3]: a,b", json!({"items": ["a", "b"]})),
        ("items[1]: a,b", json!({"items": ["a", "b"]})),
    ];

    for (input, _expected) in test_cases {
        let result = decode_default(input);
        println!("Non-strict test for '{}': {:?}", input, result);
    }
}

#[test]
fn test_delimiter_errors() {
    let mixed_delimiters = "items[3]: a,b|c";
    let result = decode_default(mixed_delimiters);

    println!("Mixed delimiter test: {:?}", result);
}

#[test]
fn test_quoting_errors() {
    let test_cases = vec![
        ("value: \"unclosed", "Unclosed string"),
        ("value: \"invalid\\x\"", "Invalid escape"),
    ];

    for (input, description) in test_cases {
        let result = decode_default(input);
        println!("Quoting error test '{}': {:?}", description, result);
    }
}

#[test]
fn test_tabular_array_errors() {
    let result = decode_default("items[2]{id,name}:\n  1,Alice\n  2");
    assert!(result.is_err(), "Should error on incomplete row");

    if let Err(e) = result {
        let err_str = e.to_string();
        assert!(
            err_str.contains("delimiter")
                || err_str.contains("field")
                || err_str.contains("Expected")
                || err_str.contains("primitive"),
            "Error should mention missing field or delimiter: {}",
            err_str
        );
    }

    let result = decode_default("items[2]{id,name}:\n  1,Alice\n  2,Bob,Extra");
    if result.is_err() {
        let err_str = result.unwrap_err().to_string();
        assert!(
            err_str.contains("delimiter")
                || err_str.contains("Expected")
                || err_str.contains("field"),
            "Should mention unexpected content: {}",
            err_str
        );
    } else {
        println!("Note: Extra fields are ignored in tabular arrays");
    }

    let result = decode_strict("items[3]{id,name}:\n  1,Alice\n  2,Bob");
    assert!(
        result.is_err(),
        "Should error on row count mismatch in strict mode"
    );

    if let Err(ToonError::LengthMismatch {
        expected, found, ..
    }) = result
    {
        assert_eq!(expected, 3);
        assert_eq!(found, 2);
    }
}

#[test]
fn test_nested_structure_errors() {
    let result = decode_default("obj:\n  key");
    assert!(result.is_err(), "Should error on incomplete nested object");

    let result = decode_default("arr[2]:\n  - item");
    assert!(result.is_err(), "Should error on incomplete nested array");
}

#[test]
fn test_depth_limit_errors() {
    let mut nested = "a:\n".to_string();
    for i in 0..60 {
        nested.push_str(&format!("{}b:\n", "  ".repeat(i + 1)));
    }
    nested.push_str(&format!("{}c: value", "  ".repeat(61)));

    let result = decode_default(&nested);
    println!("Deep nesting test: {:?}", result);
}

#[test]
fn test_empty_structure_errors() {
    let cases = vec![
        ("items[]:", "Empty array with colon"),
        ("obj{}:", "Empty object with colon"),
        ("{}", "Just braces"),
        ("[]", "Just brackets"),
    ];

    for (input, description) in cases {
        let result = decode_default(input);
        println!("Empty structure test '{}': {:?}", description, result);
    }
}

#[test]
fn test_error_messages_are_helpful() {
    let result = decode_strict("items[5]: a,b,c");

    if let Err(err) = result {
        let err_msg = err.to_string();

        assert!(
            err_msg.contains("5")
                || err_msg.contains("3")
                || err_msg.contains("expected")
                || err_msg.contains("found"),
            "Error message should contain length information: {}",
            err_msg
        );
    }
}

#[test]
fn test_parse_error_line_column() {
    let input = "line1: value\nline2: bad syntax!\nline3: value";
    let result = decode_default(input);

    if let Err(ToonError::ParseError { line, column, .. }) = result {
        println!("Parse error at line {}, column {}", line, column);
        assert!(line > 0, "Line number should be positive");
        assert!(column > 0, "Column number should be positive");
    }
}

#[test]
fn test_multiple_errors_in_input() {
    let input = "items[10]: a,b\nobj{missing,fields: x,y";
    let result = decode_default(input);

    assert!(result.is_err(), "Should error on malformed input");
}

#[test]
fn test_coercion_errors() {
    let opts = DecodeOptions::new().with_coerce_types(true);

    let result = decode("value: 123", &opts);
    assert!(result.is_ok());

    let result = decode("value: true", &opts);
    assert!(result.is_ok());

    let result = decode("value: 3.14", &opts);
    assert!(result.is_ok());
}

#[test]
fn test_no_coercion_preserves_strings() {
    let opts = DecodeOptions::new().with_coerce_types(false);

    let result = decode("value: hello", &opts).unwrap();
    assert!(result["value"].is_string());
    assert_eq!(result["value"], json!("hello"));

    let result = decode(r#"value: "123""#, &opts).unwrap();
    assert!(result["value"].is_string());
    assert_eq!(result["value"], json!("123"));

    let result = decode(r#"value: "true""#, &opts).unwrap();
    assert!(result["value"].is_string());
    assert_eq!(result["value"], json!("true"));

    let result = decode("value: 123", &opts).unwrap();
    assert!(result["value"].is_number());
    assert_eq!(result["value"], json!(123));

    let result = decode("value: true", &opts).unwrap();
    assert!(result["value"].is_boolean());
    assert_eq!(result["value"], json!(true));
}

#[test]
fn test_edge_case_values() {
    let cases = vec![
        ("value: 0", json!({"value": 0})),
        ("value: null", json!({"value": null})),
    ];

    for (input, expected) in cases {
        let result = decode_default(input);
        match result {
            Ok(val) => assert_eq!(val, expected, "Failed for input: {}", input),
            Err(e) => println!("Edge case '{}' error: {:?}", input, e),
        }
    }

    let result = decode_default("value: -0");
    match result {
        Ok(val) => {
            assert_eq!(
                val["value"],
                json!(0),
                "Negative zero is normalized to zero in JSON"
            );
        }
        Err(e) => println!("Edge case '-0' error: {:?}", e),
    }
}

#[test]
fn test_unicode_in_errors() {
    let input = "emoji: 😀🎉\nkey: value\nbad: @syntax!";
    let result = decode_default(input);

    if let Err(err) = result {
        let err_msg = err.to_string();
        println!("Unicode error handling: {}", err_msg);
        assert!(!err_msg.is_empty());
    }
}

#[test]
fn test_recovery_from_errors() {
    let valid_after_invalid = vec!["good: value\nbad syntax here\nalso_good: value"];

    for input in valid_after_invalid {
        let result = decode_default(input);
        println!("Recovery test for: {:?}", result);
    }
}

#[test]
fn test_strict_mode_indentation_errors() {
    let result = decode_strict("items[2]: a");
    assert!(
        result.is_err(),
        "Should error on insufficient items in strict mode"
    );

    if let Err(ToonError::LengthMismatch {
        expected, found, ..
    }) = result
    {
        assert_eq!(expected, 2);
        assert_eq!(found, 1);
    }
}

#[test]
fn test_quoted_key_without_colon() {
    let result = decode_default(r#""key" value"#);
    println!("Quoted key test: {:?}", result);
}

#[test]
fn test_nested_array_length_mismatches() {
    let result = decode_strict("outer[1]:\n  - items[2]: a,b\n  - items[3]: x,y");
    if result.is_err() {
        let err_str = result.unwrap_err().to_string();
        assert!(err_str.contains("3") || err_str.contains("2") || err_str.contains("length"));
    }
}

#[test]
fn test_empty_array_with_length() {
    let result = decode_strict("items[2]:");
    assert!(
        result.is_err(),
        "Should error when array header specifies length but no items provided"
    );

    let result = decode_strict("items[0]:");
    assert!(
        result.is_ok(),
        "Empty array with length 0 should parse successfully"
    );

    if let Ok(val) = result {
        assert_eq!(val["items"], json!([]));
    }
}

#[test]
fn test_tabular_array_field_count_mismatch() {
    let result = decode_default("items[2]{id,name}:\n  1\n  2,Bob");
    assert!(
        result.is_err(),
        "Should error when row has fewer fields than header"
    );
}

#[test]
fn test_invalid_array_header_syntax() {
    let cases = vec![
        ("items[", "Expected array length"),
        ("items[: a,b", "Expected array length"),
    ];

    for (input, expected_msg) in cases {
        let result = decode_default(input);
        assert!(
            result.is_err(),
            "Should error on invalid array header: {}",
            input
        );

        if let Err(e) = result {
            let err_str = e.to_string();
            assert!(
                err_str.contains(expected_msg) || err_str.contains("Parse error"),
                "Expected error about '{}' but got: {}",
                expected_msg,
                err_str
            );
        }
    }

    let result = decode_default("items{id}: a,b");
    println!("Braces without brackets test: {:?}", result);

    let result = decode_default("items]2[: a,b");
    println!("Quirky bracket syntax test: {:?}", result);
}

#[test]
fn test_missing_colon_after_key() {
    let _result = decode_default("key value");

    let result = decode_default("obj:\n  key value");
    println!("Missing colon in object: {:?}", result);
}

#[test]
fn test_error_context_information() {
    let result = decode_strict("items[5]: a,b");

    if let Err(e) = result {
        let err_str = e.to_string();

        assert!(
            err_str.contains("5")
                || err_str.contains("2")
                || err_str.contains("length")
                || err_str.contains("expected")
                || err_str.contains("found"),
            "Error should contain length information: {}",
            err_str
        );

        match e {
            ToonError::ParseError { context, .. } => {
                if let Some(ctx) = context {
                    println!(
                        "Error context has {} preceding lines, {} following lines",
                        ctx.preceding_lines.len(),
                        ctx.following_lines.len()
                    );
                }
            }
            ToonError::LengthMismatch { context, .. } => {
                if let Some(ctx) = context {
                    println!("Length mismatch context available:{}", ctx);
                }
            }
            _ => {}
        }
    }
}