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
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
// Copyright 2018 Flavien Raynaud.
// Copyright Materialize, Inc. and contributors. All rights reserved.
//
// Licensed under the Apache License, Version 2.0 (the "License");
// you may not use this file except in compliance with the License.
// You may obtain a copy of the License in the LICENSE file at the
// root of this repository, or online at
//
//     http://www.apache.org/licenses/LICENSE-2.0
//
// Unless required by applicable law or agreed to in writing, software
// distributed under the License is distributed on an "AS IS" BASIS,
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
// See the License for the specific language governing permissions and
// limitations under the License.
//
// This file is derived from the avro-rs project, available at
// https://github.com/flavray/avro-rs. It was incorporated
// directly into Materialize on March 3, 2020.
//
// The original source code is subject to the terms of the MIT license, a copy
// of which can be found in the LICENSE file at the root of this repository.

//! # avro
//! **[Apache Avro](https://avro.apache.org/)** is a data serialization system which provides rich
//! data structures and a compact, fast, binary data format.
//!
//! All data in Avro is schematized, as in the following example:
//!
//! ```text
//! {
//!     "type": "record",
//!     "name": "test",
//!     "fields": [
//!         {"name": "a", "type": "long", "default": 42},
//!         {"name": "b", "type": "string"}
//!     ]
//! }
//! ```
//!
//! There are basically two ways of handling Avro data in Rust:
//!
//! * **as Avro-specialized data types** based on an Avro schema;
//! * **as generic Rust types** with custom serialization logic implementing `AvroDecode`
//!   (currently only supports deserialization, not serialization).
//!
//! **avro** provides a way to read and write both these data representations easily and
//! efficiently.
//!
//! # Installing the library
//!
//!
//! Add to your `Cargo.toml`:
//!
//! ```text
//! [dependencies]
//! avro = "x.y"
//! ```
//!
//! Or in case you want to leverage the **Snappy** codec:
//!
//! ```text
//! [dependencies.avro]
//! version = "x.y"
//! features = ["snappy"]
//! ```
//!
//! # Defining a schema
//!
//! Avro data cannot exist without an Avro schema. Schemas **must** be used both while writing and
//! reading and they carry the information regarding the type of data we are
//! handling. Avro schemas are used for both schema validation and resolution of Avro data.
//!
//! Avro schemas are defined in **JSON** format and can just be parsed out of a raw string:
//!
//! ```
//! use mz_avro::Schema;
//!
//! let raw_schema = r#"
//!     {
//!         "type": "record",
//!         "name": "test",
//!         "fields": [
//!             {"name": "a", "type": "long", "default": 42},
//!             {"name": "b", "type": "string"}
//!         ]
//!     }
//! "#;
//!
//! // if the schema is not valid, this function will return an error
//! let schema: Schema = raw_schema.parse().unwrap();
//!
//! // schemas can be printed for debugging
//! println!("{:?}", schema);
//! ```
//!
//! For more information about schemas and what kind of information you can encapsulate in them,
//! please refer to the appropriate section of the
//! [Avro Specification](https://avro.apache.org/docs/current/spec.html#schemas).
//!
//! # Writing data
//!
//! Once we have defined a schema, we are ready to serialize data in Avro, validating them against
//! the provided schema in the process.
//!
//! **NOTE:** The library also provides a low-level interface for encoding a single datum in Avro
//! bytecode without generating markers and headers (for advanced use), but we highly recommend the
//! `Writer` interface to be totally Avro-compatible. Please read the API reference in case you are
//! interested.
//!
//! Given that the schema we defined above is that of an Avro *Record*, we are going to use the
//! associated type provided by the library to specify the data we want to serialize:
//!
//! ```
//! # use mz_avro::Schema;
//! use mz_avro::types::Record;
//! use mz_avro::Writer;
//! #
//! # let raw_schema = r#"
//! #     {
//! #         "type": "record",
//! #         "name": "test",
//! #         "fields": [
//! #             {"name": "a", "type": "long", "default": 42},
//! #             {"name": "b", "type": "string"}
//! #         ]
//! #     }
//! # "#;
//! # let schema: Schema = raw_schema.parse().unwrap();
//! // a writer needs a schema and something to write to
//! let mut writer = Writer::new(schema.clone(), Vec::new());
//!
//! // the Record type models our Record schema
//! let mut record = Record::new(schema.top_node()).unwrap();
//! record.put("a", 27i64);
//! record.put("b", "foo");
//!
//! // schema validation happens here
//! writer.append(record).unwrap();
//!
//! // flushing makes sure that all data gets encoded
//! writer.flush().unwrap();
//!
//! // this is how to get back the resulting avro bytecode
//! let encoded = writer.into_inner();
//! ```
//!
//! The vast majority of the time, schemas tend to define a record as a top-level container
//! encapsulating all the values to convert as fields and providing documentation for them, but in
//! case we want to directly define an Avro value, the library offers that capability via the
//! `Value` interface.
//!
//! ```
//! use mz_avro::types::Value;
//!
//! let mut value = Value::String("foo".to_string());
//! ```
//!
//! ## Using codecs to compress data
//!
//! Avro supports three different compression codecs when encoding data:
//!
//! * **Null**: leaves data uncompressed;
//! * **Deflate**: writes the data block using the deflate algorithm as specified in RFC 1951, and
//! typically implemented using the zlib library. Note that this format (unlike the "zlib format" in
//! RFC 1950) does not have a checksum.
//! * **Snappy**: uses Google's [Snappy](http://google.github.io/snappy/) compression library. Each
//! compressed block is followed by the 4-byte, big-endianCRC32 checksum of the uncompressed data in
//! the block. You must enable the `snappy` feature to use this codec.
//!
//! To specify a codec to use to compress data, just specify it while creating a `Writer`:
//! ```
//! # use mz_avro::Schema;
//! use mz_avro::Writer;
//! use mz_avro::Codec;
//! #
//! # let raw_schema = r#"
//! #     {
//! #         "type": "record",
//! #         "name": "test",
//! #         "fields": [
//! #             {"name": "a", "type": "long", "default": 42},
//! #             {"name": "b", "type": "string"}
//! #         ]
//! #     }
//! # "#;
//! # let schema: Schema = raw_schema.parse().unwrap();
//! let mut writer = Writer::with_codec(schema, Vec::new(), Codec::Deflate);
//! ```
//!
//! # Reading data
//!
//! As far as reading Avro encoded data goes, we can just use the schema encoded with the data to
//! read them. The library will do it automatically for us, as it already does for the compression
//! codec:
//!
//! ```
//!
//! use mz_avro::Reader;
//! # use mz_avro::Schema;
//! # use mz_avro::types::Record;
//! # use mz_avro::Writer;
//! #
//! # let raw_schema = r#"
//! #     {
//! #         "type": "record",
//! #         "name": "test",
//! #         "fields": [
//! #             {"name": "a", "type": "long", "default": 42},
//! #             {"name": "b", "type": "string"}
//! #         ]
//! #     }
//! # "#;
//! # let schema: Schema = raw_schema.parse().unwrap();
//! # let mut writer = Writer::new(schema.clone(), Vec::new());
//! # let mut record = Record::new(schema.top_node()).unwrap();
//! # record.put("a", 27i64);
//! # record.put("b", "foo");
//! # writer.append(record).unwrap();
//! # writer.flush().unwrap();
//! # let input = writer.into_inner();
//! // reader creation can fail in case the input to read from is not Avro-compatible or malformed
//! let reader = Reader::new(&input[..]).unwrap();
//! ```
//!
//! In case, instead, we want to specify a different (but compatible) reader schema from the schema
//! the data has been written with, we can just do as the following:
//! ```
//! use mz_avro::Schema;
//! use mz_avro::Reader;
//! # use mz_avro::types::Record;
//! # use mz_avro::Writer;
//! #
//! # let writer_raw_schema = r#"
//! #     {
//! #         "type": "record",
//! #         "name": "test",
//! #         "fields": [
//! #             {"name": "a", "type": "long", "default": 42},
//! #             {"name": "b", "type": "string"}
//! #         ]
//! #     }
//! # "#;
//! # let writer_schema: Schema = writer_raw_schema.parse().unwrap();
//! # let mut writer = Writer::new(writer_schema.clone(), Vec::new());
//! # let mut record = Record::new(writer_schema.top_node()).unwrap();
//! # record.put("a", 27i64);
//! # record.put("b", "foo");
//! # writer.append(record).unwrap();
//! # writer.flush().unwrap();
//! # let input = writer.into_inner();
//!
//! let reader_raw_schema = r#"
//!     {
//!         "type": "record",
//!         "name": "test",
//!         "fields": [
//!             {"name": "a", "type": "long", "default": 42},
//!             {"name": "b", "type": "string"},
//!             {"name": "c", "type": "long", "default": 43}
//!         ]
//!     }
//! "#;
//!
//! let reader_schema: Schema = reader_raw_schema.parse().unwrap();
//!
//! // reader creation can fail in case the input to read from is not Avro-compatible or malformed
//! let reader = Reader::with_schema(&reader_schema, &input[..]).unwrap();
//! ```
//!
//! The library will also automatically perform schema resolution while reading the data.
//!
//! For more information about schema compatibility and resolution, please refer to the
//! [Avro Specification](https://avro.apache.org/docs/current/spec.html#schemas).
//!
//! There are two ways to handle deserializing Avro data in Rust, as you can see below.
//!
//! **NOTE:** The library also provides a low-level interface for decoding a single datum in Avro
//! bytecode without markers and header (for advanced use), but we highly recommend the `Reader`
//! interface to leverage all Avro features. Please read the API reference in case you are
//! interested.
//!
//!
//! ## The avro way
//!
//! We can just read directly instances of `Value` out of the `Reader` iterator:
//!
//! ```
//! # use mz_avro::Schema;
//! # use mz_avro::types::Record;
//! # use mz_avro::Writer;
//! use mz_avro::Reader;
//! #
//! # let raw_schema = r#"
//! #     {
//! #         "type": "record",
//! #         "name": "test",
//! #         "fields": [
//! #             {"name": "a", "type": "long", "default": 42},
//! #             {"name": "b", "type": "string"}
//! #         ]
//! #     }
//! # "#;
//! # let schema: Schema = raw_schema.parse().unwrap();
//! # let mut writer = Writer::new(schema.clone(), Vec::new());
//! # let mut record = Record::new(schema.top_node()).unwrap();
//! # record.put("a", 27i64);
//! # record.put("b", "foo");
//! # writer.append(record).unwrap();
//! # writer.flush().unwrap();
//! # let input = writer.into_inner();
//! let mut reader = Reader::new(&input[..]).unwrap();
//!
//! // value is a Result of an Avro Value in case the read operation fails
//! for value in reader {
//!     println!("{:?}", value.unwrap());
//! }
//!
//! ```
//!
//! ## Custom deserialization (advanced)
//!
//! It is possible to avoid the intermediate stage of decoding to `Value`,
//! by implementing `AvroDecode` for one or more structs that will determine how to decode various schema pieces.
//!
//! This API is in flux, and more complete documentation is coming soon. For now,
//! [Materialize](https://github.com/MaterializeInc/materialize/blob/main/src/interchange/src/avro.rs)
//! furnishes the most complete example.

// TODO(benesch): remove this once this crate no longer makes use of potentially
// dangerous `as` conversions.
#![allow(clippy::as_conversions)]

mod codec;
mod decode;
mod reader;
mod util;
mod writer;

pub mod encode;
pub mod error;
pub mod schema;
pub mod types;

pub use crate::codec::Codec;
pub use crate::decode::public_decoders::*;
pub use crate::decode::{
    give_value, AvroArrayAccess, AvroDecodable, AvroDecode, AvroDeserializer, AvroFieldAccess,
    AvroMapAccess, AvroRead, AvroRecordAccess, GeneralDeserializer, Skip, StatefulAvroDecodable,
    ValueOrReader,
};
pub use crate::encode::encode as encode_unchecked;
pub use crate::reader::{from_avro_datum, Block, BlockIter, Reader};
pub use crate::schema::{ParseSchemaError, Schema};
pub use crate::types::SchemaResolutionError;
pub use crate::writer::{to_avro_datum, write_avro_datum, ValidationError, Writer};

#[cfg(test)]
mod tests {
    use std::str::FromStr;

    use crate::reader::Reader;
    use crate::schema::Schema;
    use crate::types::{Record, Value};

    use super::*;

    //TODO: move where it fits better
    #[mz_ore::test]
    #[cfg_attr(miri, ignore)] // unsupported operation: inline assembly is not supported
    fn test_enum_default() {
        let writer_raw_schema = r#"
            {
                "type": "record",
                "name": "test",
                "fields": [
                    {"name": "a", "type": "long", "default": 42},
                    {"name": "b", "type": "string"}
                ]
            }
        "#;
        let reader_raw_schema = r#"
            {
                "type": "record",
                "name": "test",
                "fields": [
                    {"name": "a", "type": "long", "default": 42},
                    {"name": "b", "type": "string"},
                    {
                        "name": "c",
                        "type": {
                            "type": "enum",
                            "name": "suit",
                            "symbols": ["diamonds", "spades", "clubs", "hearts"]
                        },
                        "default": "spades"
                    }
                ]
            }
        "#;
        let writer_schema = Schema::from_str(writer_raw_schema).unwrap();
        let reader_schema = Schema::from_str(reader_raw_schema).unwrap();
        let mut writer = Writer::with_codec(writer_schema.clone(), Vec::new(), Codec::Null);
        let mut record = Record::new(writer_schema.top_node()).unwrap();
        record.put("a", 27i64);
        record.put("b", "foo");
        writer.append(record).unwrap();
        writer.flush().unwrap();
        let input = writer.into_inner();
        let mut reader = Reader::with_schema(&reader_schema, &input[..]).unwrap();
        assert_eq!(
            reader.next().unwrap().unwrap(),
            Value::Record(vec![
                ("a".to_string(), Value::Long(27)),
                ("b".to_string(), Value::String("foo".to_string())),
                ("c".to_string(), Value::Enum(1, "spades".to_string())),
            ])
        );
        assert!(reader.next().is_none());
    }

    //TODO: move where it fits better
    #[mz_ore::test]
    #[cfg_attr(miri, ignore)] // unsupported operation: inline assembly is not supported
    fn test_enum_string_value() {
        let raw_schema = r#"
            {
                "type": "record",
                "name": "test",
                "fields": [
                    {"name": "a", "type": "long", "default": 42},
                    {"name": "b", "type": "string"},
                    {
                        "name": "c",
                        "type": {
                            "type": "enum",
                            "name": "suit",
                            "symbols": ["diamonds", "spades", "clubs", "hearts"]
                        },
                        "default": "spades"
                    }
                ]
            }
        "#;
        let schema = Schema::from_str(raw_schema).unwrap();
        let mut writer = Writer::with_codec(schema.clone(), Vec::new(), Codec::Null);
        let mut record = Record::new(schema.top_node()).unwrap();
        record.put("a", 27i64);
        record.put("b", "foo");
        record.put("c", "clubs");
        writer.append(record).unwrap();
        writer.flush().unwrap();
        let input = writer.into_inner();
        let mut reader = Reader::with_schema(&schema, &input[..]).unwrap();
        assert_eq!(
            reader.next().unwrap().unwrap(),
            Value::Record(vec![
                ("a".to_string(), Value::Long(27)),
                ("b".to_string(), Value::String("foo".to_string())),
                ("c".to_string(), Value::Enum(2, "clubs".to_string())),
            ])
        );
        assert!(reader.next().is_none());
    }

    //TODO: move where it fits better
    #[mz_ore::test]
    #[cfg_attr(miri, ignore)] // unsupported operation: inline assembly is not supported
    fn test_enum_resolution() {
        let writer_raw_schema = r#"
            {
                "type": "record",
                "name": "test",
                "fields": [
                    {"name": "a", "type": "long", "default": 42},
                    {"name": "b", "type": "string"},
                    {
                        "name": "c",
                        "type": {
                            "type": "enum",
                            "name": "suit",
                            "symbols": ["diamonds", "spades", "clubs", "hearts"]
                        },
                        "default": "spades"
                    }
                ]
            }
        "#;
        let reader_raw_schema = r#"
            {
                "type": "record",
                "name": "test",
                "fields": [
                    {"name": "a", "type": "long", "default": 42},
                    {"name": "b", "type": "string"},
                    {
                        "name": "c",
                        "type": {
                            "type": "enum",
                            "name": "suit",
                            "symbols": ["diamonds", "spades", "ninja", "hearts"]
                        },
                        "default": "spades"
                    }
                ]
            }
        "#;
        let writer_schema = Schema::from_str(writer_raw_schema).unwrap();
        let reader_schema = Schema::from_str(reader_raw_schema).unwrap();
        let mut writer = Writer::with_codec(writer_schema.clone(), Vec::new(), Codec::Null);
        let mut record = Record::new(writer_schema.top_node()).unwrap();
        record.put("a", 27i64);
        record.put("b", "foo");
        record.put("c", "clubs");
        writer.append(record).unwrap();
        writer.flush().unwrap();
        let input = writer.into_inner();
        let mut reader = Reader::with_schema(&reader_schema, &input[..]).unwrap();
        assert!(reader.next().unwrap().is_err());
        assert!(reader.next().is_none());
    }

    //TODO: move where it fits better
    #[mz_ore::test]
    fn test_enum_no_reader_schema() {
        let writer_raw_schema = r#"
            {
                "type": "record",
                "name": "test",
                "fields": [
                    {"name": "a", "type": "long", "default": 42},
                    {"name": "b", "type": "string"},
                    {
                        "name": "c",
                        "type": {
                            "type": "enum",
                            "name": "suit",
                            "symbols": ["diamonds", "spades", "clubs", "hearts"]
                        },
                        "default": "spades"
                    }
                ]
            }
        "#;
        let writer_schema = Schema::from_str(writer_raw_schema).unwrap();
        let mut writer = Writer::with_codec(writer_schema.clone(), Vec::new(), Codec::Null);
        let mut record = Record::new(writer_schema.top_node()).unwrap();
        record.put("a", 27i64);
        record.put("b", "foo");
        record.put("c", "clubs");
        writer.append(record).unwrap();
        writer.flush().unwrap();
        let input = writer.into_inner();
        let mut reader = Reader::new(&input[..]).unwrap();
        assert_eq!(
            reader.next().unwrap().unwrap(),
            Value::Record(vec![
                ("a".to_string(), Value::Long(27)),
                ("b".to_string(), Value::String("foo".to_string())),
                ("c".to_string(), Value::Enum(2, "clubs".to_string())),
            ])
        );
    }
    #[mz_ore::test]
    fn test_datetime_value() {
        let writer_raw_schema = r#"{
        "type": "record",
        "name": "dttest",
        "fields": [
            {
                "name": "a",
                "type": {
                    "type": "long",
                    "logicalType": "timestamp-micros"
                }
            }
        ]}"#;
        let writer_schema = Schema::from_str(writer_raw_schema).unwrap();
        let mut writer = Writer::with_codec(writer_schema.clone(), Vec::new(), Codec::Null);
        let mut record = Record::new(writer_schema.top_node()).unwrap();
        let dt = chrono::NaiveDateTime::from_timestamp_opt(1_000, 995_000_000).unwrap();
        record.put("a", types::Value::Timestamp(dt));
        writer.append(record).unwrap();
        writer.flush().unwrap();
        let input = writer.into_inner();
        let mut reader = Reader::new(&input[..]).unwrap();
        assert_eq!(
            reader.next().unwrap().unwrap(),
            Value::Record(vec![("a".to_string(), Value::Timestamp(dt)),])
        );
    }

    #[mz_ore::test]
    fn test_malformed_length() {
        let raw_schema = r#"
            {
                "type": "record",
                "name": "test",
                "fields": [
                    {"name": "a", "type": "long", "default": 42},
                    {"name": "b", "type": "string"}
                ]
            }
        "#;

        let schema = Schema::from_str(raw_schema).unwrap();

        // Would allocated 18446744073709551605 bytes
        let malformed: &[u8] = &[0x3e, 0x15, 0xff, 0x1f, 0x15, 0xff];

        let value = from_avro_datum(&schema, &mut &malformed[..]);
        assert!(value.is_err());
    }
}