yggdryl 0.1.0 → 0.1.1
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/LICENSE +202 -0
- package/README.md +256 -19
- package/benchmarks/codec.js +133 -0
- package/benchmarks/defaults.js +66 -0
- package/benchmarks/io.js +61 -0
- package/benchmarks/records.js +121 -0
- package/benchmarks/schema.js +84 -0
- package/binding.d.ts +1176 -0
- package/binding.js +1874 -0
- package/defaults.js +195 -0
- package/fields.js +243 -0
- package/index.d.ts +1744 -34
- package/index.js +411 -266
- package/package.json +48 -18
- package/records.js +441 -0
- package/values.js +64 -0
- package/yggdryl.darwin-arm64.node +0 -0
- package/yggdryl.darwin-x64.node +0 -0
- package/yggdryl.linux-arm64-gnu.node +0 -0
- package/yggdryl.linux-x64-gnu.node +0 -0
- package/yggdryl.win32-x64-msvc.node +0 -0
package/LICENSE
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
1
|
+
Apache License
|
|
2
|
+
Version 2.0, January 2004
|
|
3
|
+
http://www.apache.org/licenses/
|
|
4
|
+
|
|
5
|
+
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
|
|
6
|
+
|
|
7
|
+
1. Definitions.
|
|
8
|
+
|
|
9
|
+
"License" shall mean the terms and conditions for use, reproduction,
|
|
10
|
+
and distribution as defined by Sections 1 through 9 of this document.
|
|
11
|
+
|
|
12
|
+
"Licensor" shall mean the copyright owner or entity authorized by
|
|
13
|
+
the copyright owner that is granting the License.
|
|
14
|
+
|
|
15
|
+
"Legal Entity" shall mean the union of the acting entity and all
|
|
16
|
+
other entities that control, are controlled by, or are under common
|
|
17
|
+
control with that entity. For the purposes of this definition,
|
|
18
|
+
"control" means (i) the power, direct or indirect, to cause the
|
|
19
|
+
direction or management of such entity, whether by contract or
|
|
20
|
+
otherwise, or (ii) ownership of fifty percent (50%) or more of the
|
|
21
|
+
outstanding shares, or (iii) beneficial ownership of such entity.
|
|
22
|
+
|
|
23
|
+
"You" (or "Your") shall mean an individual or Legal Entity
|
|
24
|
+
exercising permissions granted by this License.
|
|
25
|
+
|
|
26
|
+
"Source" form shall mean the preferred form for making modifications,
|
|
27
|
+
including but not limited to software source code, documentation
|
|
28
|
+
source, and configuration files.
|
|
29
|
+
|
|
30
|
+
"Object" form shall mean any form resulting from mechanical
|
|
31
|
+
transformation or translation of a Source form, including but
|
|
32
|
+
not limited to compiled object code, generated documentation,
|
|
33
|
+
and conversions to other media types.
|
|
34
|
+
|
|
35
|
+
"Work" shall mean the work of authorship, whether in Source or
|
|
36
|
+
Object form, made available under the License, as indicated by a
|
|
37
|
+
copyright notice that is included in or attached to the work
|
|
38
|
+
(an example is provided in the Appendix below).
|
|
39
|
+
|
|
40
|
+
"Derivative Works" shall mean any work, whether in Source or Object
|
|
41
|
+
form, that is based on (or derived from) the Work and for which the
|
|
42
|
+
editorial revisions, annotations, elaborations, or other modifications
|
|
43
|
+
represent, as a whole, an original work of authorship. For the purposes
|
|
44
|
+
of this License, Derivative Works shall not include works that remain
|
|
45
|
+
separable from, or merely link (or bind by name) to the interfaces of,
|
|
46
|
+
the Work and Derivative Works thereof.
|
|
47
|
+
|
|
48
|
+
"Contribution" shall mean any work of authorship, including
|
|
49
|
+
the original version of the Work and any modifications or additions
|
|
50
|
+
to that Work or Derivative Works thereof, that is intentionally
|
|
51
|
+
submitted to Licensor for inclusion in the Work by the copyright owner
|
|
52
|
+
or by an individual or Legal Entity authorized to submit on behalf of
|
|
53
|
+
the copyright owner. For the purposes of this definition, "submitted"
|
|
54
|
+
means any form of electronic, verbal, or written communication sent
|
|
55
|
+
to the Licensor or its representatives, including but not limited to
|
|
56
|
+
communication on electronic mailing lists, source code control systems,
|
|
57
|
+
and issue tracking systems that are managed by, or on behalf of, the
|
|
58
|
+
Licensor for the purpose of discussing and improving the Work, but
|
|
59
|
+
excluding communication that is conspicuously marked or otherwise
|
|
60
|
+
designated in writing by the copyright owner as "Not a Contribution."
|
|
61
|
+
|
|
62
|
+
"Contributor" shall mean Licensor and any individual or Legal Entity
|
|
63
|
+
on behalf of whom a Contribution has been received by Licensor and
|
|
64
|
+
subsequently incorporated within the Work.
|
|
65
|
+
|
|
66
|
+
2. Grant of Copyright License. Subject to the terms and conditions of
|
|
67
|
+
this License, each Contributor hereby grants to You a perpetual,
|
|
68
|
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
|
69
|
+
copyright license to reproduce, prepare Derivative Works of,
|
|
70
|
+
publicly display, publicly perform, sublicense, and distribute the
|
|
71
|
+
Work and such Derivative Works in Source or Object form.
|
|
72
|
+
|
|
73
|
+
3. Grant of Patent License. Subject to the terms and conditions of
|
|
74
|
+
this License, each Contributor hereby grants to You a perpetual,
|
|
75
|
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
|
76
|
+
(except as stated in this section) patent license to make, have made,
|
|
77
|
+
use, offer to sell, sell, import, and otherwise transfer the Work,
|
|
78
|
+
where such license applies only to those patent claims licensable
|
|
79
|
+
by such Contributor that are necessarily infringed by their
|
|
80
|
+
Contribution(s) alone or by combination of their Contribution(s)
|
|
81
|
+
with the Work to which such Contribution(s) was submitted. If You
|
|
82
|
+
institute patent litigation against any entity (including a
|
|
83
|
+
cross-claim or counterclaim in a lawsuit) alleging that the Work
|
|
84
|
+
or a Contribution incorporated within the Work constitutes direct
|
|
85
|
+
or contributory patent infringement, then any patent licenses
|
|
86
|
+
granted to You under this License for that Work shall terminate
|
|
87
|
+
as of the date such litigation is filed.
|
|
88
|
+
|
|
89
|
+
4. Redistribution. You may reproduce and distribute copies of the
|
|
90
|
+
Work or Derivative Works thereof in any medium, with or without
|
|
91
|
+
modifications, and in Source or Object form, provided that You
|
|
92
|
+
meet the following conditions:
|
|
93
|
+
|
|
94
|
+
(a) You must give any other recipients of the Work or
|
|
95
|
+
Derivative Works a copy of this License; and
|
|
96
|
+
|
|
97
|
+
(b) You must cause any modified files to carry prominent notices
|
|
98
|
+
stating that You changed the files; and
|
|
99
|
+
|
|
100
|
+
(c) You must retain, in the Source form of any Derivative Works
|
|
101
|
+
that You distribute, all copyright, patent, trademark, and
|
|
102
|
+
attribution notices from the Source form of the Work,
|
|
103
|
+
excluding those notices that do not pertain to any part of
|
|
104
|
+
the Derivative Works; and
|
|
105
|
+
|
|
106
|
+
(d) If the Work includes a "NOTICE" text file as part of its
|
|
107
|
+
distribution, then any Derivative Works that You distribute must
|
|
108
|
+
include a readable copy of the attribution notices contained
|
|
109
|
+
within such NOTICE file, excluding those notices that do not
|
|
110
|
+
pertain to any part of the Derivative Works, in at least one
|
|
111
|
+
of the following places: within a NOTICE text file distributed
|
|
112
|
+
as part of the Derivative Works; within the Source form or
|
|
113
|
+
documentation, if provided along with the Derivative Works; or,
|
|
114
|
+
within a display generated by the Derivative Works, if and
|
|
115
|
+
wherever such third-party notices normally appear. The contents
|
|
116
|
+
of the NOTICE file are for informational purposes only and
|
|
117
|
+
do not modify the License. You may add Your own attribution
|
|
118
|
+
notices within Derivative Works that You distribute, alongside
|
|
119
|
+
or as an addendum to the NOTICE text from the Work, provided
|
|
120
|
+
that such additional attribution notices cannot be construed
|
|
121
|
+
as modifying the License.
|
|
122
|
+
|
|
123
|
+
You may add Your own copyright statement to Your modifications and
|
|
124
|
+
may provide additional or different license terms and conditions
|
|
125
|
+
for use, reproduction, or distribution of Your modifications, or
|
|
126
|
+
for any such Derivative Works as a whole, provided Your use,
|
|
127
|
+
reproduction, and distribution of the Work otherwise complies with
|
|
128
|
+
the conditions stated in this License.
|
|
129
|
+
|
|
130
|
+
5. Submission of Contributions. Unless You explicitly state otherwise,
|
|
131
|
+
any Contribution intentionally submitted for inclusion in the Work
|
|
132
|
+
by You to the Licensor shall be under the terms and conditions of
|
|
133
|
+
this License, without any additional terms or conditions.
|
|
134
|
+
Notwithstanding the above, nothing herein shall supersede or modify
|
|
135
|
+
the terms of any separate license agreement you may have executed
|
|
136
|
+
with Licensor regarding such Contributions.
|
|
137
|
+
|
|
138
|
+
6. Trademarks. This License does not grant permission to use the trade
|
|
139
|
+
names, trademarks, service marks, or product names of the Licensor,
|
|
140
|
+
except as required for reasonable and customary use in describing the
|
|
141
|
+
origin of the Work and reproducing the content of the NOTICE file.
|
|
142
|
+
|
|
143
|
+
7. Disclaimer of Warranty. Unless required by applicable law or
|
|
144
|
+
agreed to in writing, Licensor provides the Work (and each
|
|
145
|
+
Contributor provides its Contributions) on an "AS IS" BASIS,
|
|
146
|
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
|
|
147
|
+
implied, including, without limitation, any warranties or conditions
|
|
148
|
+
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
|
|
149
|
+
PARTICULAR PURPOSE. You are solely responsible for determining the
|
|
150
|
+
appropriateness of using or redistributing the Work and assume any
|
|
151
|
+
risks associated with Your exercise of permissions under this License.
|
|
152
|
+
|
|
153
|
+
8. Limitation of Liability. In no event and under no legal theory,
|
|
154
|
+
whether in tort (including negligence), contract, or otherwise,
|
|
155
|
+
unless required by applicable law (such as deliberate and grossly
|
|
156
|
+
negligent acts) or agreed to in writing, shall any Contributor be
|
|
157
|
+
liable to You for damages, including any direct, indirect, special,
|
|
158
|
+
incidental, or consequential damages of any character arising as a
|
|
159
|
+
result of this License or out of the use or inability to use the
|
|
160
|
+
Work (including but not limited to damages for loss of goodwill,
|
|
161
|
+
work stoppage, computer failure or malfunction, or any and all
|
|
162
|
+
other commercial damages or losses), even if such Contributor
|
|
163
|
+
has been advised of the possibility of such damages.
|
|
164
|
+
|
|
165
|
+
9. Accepting Warranty or Additional Liability. While redistributing
|
|
166
|
+
the Work or Derivative Works thereof, You may choose to offer,
|
|
167
|
+
and charge a fee for, acceptance of support, warranty, indemnity,
|
|
168
|
+
or other liability obligations and/or rights consistent with this
|
|
169
|
+
License. However, in accepting such obligations, You may act only
|
|
170
|
+
on Your own behalf and on Your sole responsibility, not on behalf
|
|
171
|
+
of any other Contributor, and only if You agree to indemnify,
|
|
172
|
+
defend, and hold each Contributor harmless for any liability
|
|
173
|
+
incurred by, or claims asserted against, such Contributor by reason
|
|
174
|
+
of your accepting any such warranty or additional liability.
|
|
175
|
+
|
|
176
|
+
END OF TERMS AND CONDITIONS
|
|
177
|
+
|
|
178
|
+
APPENDIX: How to apply the Apache License to your work.
|
|
179
|
+
|
|
180
|
+
To apply the Apache License to your work, attach the following
|
|
181
|
+
boilerplate notice, with the fields enclosed by brackets "[]"
|
|
182
|
+
replaced with your own identifying information. (Don't include
|
|
183
|
+
the brackets!) The text should be enclosed in the appropriate
|
|
184
|
+
comment syntax for the file format. We also recommend that a
|
|
185
|
+
file or class name and description of purpose be included on the
|
|
186
|
+
same "printed page" as the copyright notice for easier
|
|
187
|
+
identification within third-party archives.
|
|
188
|
+
|
|
189
|
+
Copyright [yyyy] [name of copyright owner]
|
|
190
|
+
|
|
191
|
+
Licensed under the Apache License, Version 2.0 (the "License");
|
|
192
|
+
you may not use this file except in compliance with the License.
|
|
193
|
+
You may obtain a copy of the License at
|
|
194
|
+
|
|
195
|
+
http://www.apache.org/licenses/LICENSE-2.0
|
|
196
|
+
|
|
197
|
+
Unless required by applicable law or agreed to in writing, software
|
|
198
|
+
distributed under the License is distributed on an "AS IS" BASIS,
|
|
199
|
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
200
|
+
See the License for the specific language governing permissions and
|
|
201
|
+
limitations under the License.
|
|
202
|
+
|
package/README.md
CHANGED
|
@@ -1,30 +1,267 @@
|
|
|
1
|
-
#
|
|
1
|
+
# Yggdryl for JavaScript
|
|
2
2
|
|
|
3
|
-
|
|
4
|
-
|
|
3
|
+
```javascript
|
|
4
|
+
const { json, toml, yaml } = require('yggdryl')
|
|
5
|
+
|
|
6
|
+
const bytes = json.dumps({ symbol: 'AAPL', price: 224.62 })
|
|
7
|
+
const trade = json.loads(bytes)
|
|
8
|
+
const config = toml.loads('symbol = "AAPL"\nprice = 224.62\n')
|
|
9
|
+
const documents = yaml.loadsAll(Buffer.from('---\nsymbol: AAPL\n---\nsymbol: MSFT\n'))
|
|
10
|
+
|
|
11
|
+
console.assert(Buffer.isBuffer(bytes))
|
|
12
|
+
console.assert(trade.symbol === 'AAPL')
|
|
13
|
+
console.assert(config.symbol === 'AAPL')
|
|
14
|
+
console.assert(documents[1].symbol === 'MSFT')
|
|
15
|
+
```
|
|
16
|
+
|
|
17
|
+
JSON, YAML, and TOML APIs are byte-first and preserve binary
|
|
18
|
+
values, large integers, dates, maps, sets, and typed arrays. `load` and `dump`
|
|
19
|
+
also accept paths, descriptors, file URLs, and Node or WHATWG streams. Primitive
|
|
20
|
+
strings are content unless they name an existing regular file; `loads` always
|
|
21
|
+
treats them as content. Real paths redirect to Rust reader/writer methods
|
|
22
|
+
without a whole-file JavaScript buffer. Stream overloads are asynchronous and
|
|
23
|
+
apply writable backpressure without closing caller-owned I/O.
|
|
24
|
+
|
|
25
|
+
```javascript
|
|
26
|
+
const { Readable, Writable } = require('node:stream')
|
|
27
|
+
const { json } = require('yggdryl')
|
|
28
|
+
|
|
29
|
+
async function main() {
|
|
30
|
+
const value = await json.load(Readable.from(['{"id":', '42}']))
|
|
31
|
+
await json.dump(value, new Writable({
|
|
32
|
+
write(chunk, _encoding, done) {
|
|
33
|
+
process.stdout.write(chunk, done)
|
|
34
|
+
},
|
|
35
|
+
}))
|
|
36
|
+
}
|
|
37
|
+
|
|
38
|
+
main()
|
|
39
|
+
```
|
|
40
|
+
|
|
41
|
+
`loadAll` redirects an async byte source to the lazy `loadAllStream` iterator;
|
|
42
|
+
`dumpAll` redirects a writable destination to `dumpAllStream`. Single-document
|
|
43
|
+
stream reads use one bounded buffer because Node's async reader cannot be
|
|
44
|
+
passed to synchronous Rust `Read`; multi-document reads and writes stay
|
|
45
|
+
incremental. Buffer, ArrayBuffer, SharedArrayBuffer, DataView, and typed-array
|
|
46
|
+
offsets are all preserved exactly.
|
|
47
|
+
|
|
48
|
+
TOML is deliberately single-document and exposes only `loads`, `load`,
|
|
49
|
+
`dumps`, `dump`, `loadStream`, and `dumpStream`. Generic `codec` operations
|
|
50
|
+
infer `.toml` paths in Rust or accept explicit `format: 'toml'` for content.
|
|
51
|
+
|
|
52
|
+
```javascript
|
|
53
|
+
const { DataType, Field, MediaType, MimeType, Uri } = require('yggdryl')
|
|
54
|
+
|
|
55
|
+
const type = DataType.fromString('struct<symbol:string,price:decimal(18,4)>')
|
|
56
|
+
const coarseClock = DataType.time('milliseconds')
|
|
57
|
+
const preciseClock = DataType.time('nanoseconds')
|
|
58
|
+
const field = new Field('trade', type, false, { source: 'book' })
|
|
59
|
+
field.setTableName('trades')
|
|
60
|
+
field.setParquetFieldId(17)
|
|
61
|
+
field.setLocation('s3://warehouse/trades/data.arrow')
|
|
62
|
+
field.setProperty('postgres', 'type', 'jsonb')
|
|
63
|
+
const file = Uri.fromPath('C:\\data\\trades.arrow')
|
|
64
|
+
const encoded = Uri.fromString('https://example.test/trades.csv.gz')
|
|
65
|
+
|
|
66
|
+
console.assert(Field.fromString(field.toString()).equals(field))
|
|
67
|
+
console.assert(coarseClock.kind === 'time32')
|
|
68
|
+
console.assert(preciseClock.kind === 'time64')
|
|
69
|
+
console.assert(field.parquetFieldId === 17)
|
|
70
|
+
console.assert(field.get('PARQUET:field_id') === '17')
|
|
71
|
+
console.assert(field.location.scheme === 's3')
|
|
72
|
+
console.assert(field.getProperty('postgres', 'type') === 'jsonb')
|
|
73
|
+
console.assert(file.toString() === 'file:///C:/data/trades.arrow')
|
|
74
|
+
console.assert(file.toPath() === 'C:/data/trades.arrow')
|
|
75
|
+
console.assert(encoded.mediaType.base.equals(MimeType.fromString('text/csv')))
|
|
76
|
+
encoded.setMediaType(MediaType.fromParts('application/json', ['application/gzip']))
|
|
77
|
+
console.assert(encoded.fileName === 'trades.json.gz')
|
|
78
|
+
```
|
|
79
|
+
|
|
80
|
+
The Node-API package exposes native `DataType`, `Field`, `IOBase`, `MimeType`,
|
|
81
|
+
`MediaType`, `Timezone`, `Uri`, `Url`, `Urn`, and `Value` values, the record pair
|
|
82
|
+
`BatchReader` and `RecordOptions`, and the `iceberg` namespace over all of them.
|
|
83
|
+
Recursive parsing, validation, Arrow casting, record scalar conversion, codec
|
|
84
|
+
conversion, ordering, stable hashing, metadata, and path normalization stay in
|
|
85
|
+
Rust.
|
|
86
|
+
`DataType.time(unit)` and `fields.time(name, unit)` require an explicit unit;
|
|
87
|
+
seconds/milliseconds select Time32 and microseconds/nanoseconds select Time64.
|
|
88
|
+
They accept the same native unit aliases as datatype parsing and reject
|
|
89
|
+
interval layouts.
|
|
90
|
+
|
|
91
|
+
```javascript
|
|
92
|
+
const { Record, fields } = require('yggdryl')
|
|
93
|
+
|
|
94
|
+
const Trade = Record.define('Trade', [
|
|
95
|
+
fields.int64('id'),
|
|
96
|
+
fields.utf8('symbol'),
|
|
97
|
+
fields.decimal128('price', 18, 4),
|
|
98
|
+
])
|
|
99
|
+
const rows = [
|
|
100
|
+
new Trade({ id: 1n, symbol: 'AAPL', price: 2246200n }),
|
|
101
|
+
new Trade({ id: 2n, symbol: 'MSFT', price: 4187900n }),
|
|
102
|
+
]
|
|
103
|
+
|
|
104
|
+
const batch = Trade.intoArrowRecordBatch(rows)
|
|
105
|
+
const restored = [...Trade.fromArrowRecordBatch(batch)]
|
|
106
|
+
|
|
107
|
+
console.assert(restored[0].symbol === 'AAPL')
|
|
108
|
+
console.assert(restored[1].price === 4187900n)
|
|
109
|
+
```
|
|
110
|
+
|
|
111
|
+
Each defined class owns one shared native Record schema/name index. Apache
|
|
112
|
+
Arrow JS conversion is an explicit copied IPC boundary: it never serializes per
|
|
113
|
+
property access and does not claim zero-copy C Data interoperability. Use
|
|
114
|
+
`intoArrowRecordBatches` for bounded output, `fromArrowRecordBatchReader` for
|
|
115
|
+
batch-bounded input, and `intoArrowIPC`/`fromArrowIPC` for every physical layout
|
|
116
|
+
representable by the core `yggdryl::arrow` IPC runtime. The Apache Arrow
|
|
117
|
+
dependency loads only when an Arrow adapter is used.
|
|
118
|
+
|
|
119
|
+
`DataType.castArrowArray`, `Field.castArrowArray`, `DataType.castArrowBatch`,
|
|
120
|
+
and `Field.castArrowBatch` route copied Apache Arrow JS holders through the one
|
|
121
|
+
native `yggdryl::arrow` cast engine. Exact no-op casts preserve the original
|
|
122
|
+
Vector or RecordBatch identity; changed outputs follow `{safe: true}` by
|
|
123
|
+
default and never use a JavaScript conversion table.
|
|
124
|
+
|
|
125
|
+
Tabular cursor reads validate the declared source schema before any optional
|
|
126
|
+
target projection. Getters use a non-consuming snapshot. Overwrite, append,
|
|
127
|
+
indexed set, and positional upsert compute a complete validated replacement
|
|
128
|
+
before invoking one private atomic overwrite-all hook. `overwriteRecords`,
|
|
129
|
+
`appendRecords`, and `upsertRecords` provide the matching class-bound bulk
|
|
130
|
+
helpers and validate their options and source-to-backend cast plan before
|
|
131
|
+
consuming a one-shot row iterable. Dataset iterables likewise stop at their
|
|
132
|
+
first incompatible batch. Numeric selectors and matching table URLs with a
|
|
133
|
+
`#N` fragment address a batch; the exact table URL addresses the whole resource.
|
|
134
|
+
Tabular and dataset schema getters retain a stable canonical Arrow JS identity
|
|
135
|
+
and fingerprint-repair caller mutation from native state before reuse.
|
|
136
|
+
|
|
137
|
+
Run `npm run bench:record` or `npm run bench:tabular` to measure native Record
|
|
138
|
+
behavior and the copied-IPC read, cast, overwrite, indexed mutation, in-memory
|
|
139
|
+
table, and dataset paths separately. Set `YGGDRYL_BENCH_ITERATIONS` to change the
|
|
140
|
+
default sample count.
|
|
141
|
+
|
|
142
|
+
```javascript
|
|
143
|
+
const { Record, fields } = require('yggdryl')
|
|
5
144
|
|
|
6
|
-
|
|
145
|
+
const payload = fields.struct('payload', [
|
|
146
|
+
fields.int64('count'),
|
|
147
|
+
fields.utf8('note', { nullable: true }),
|
|
148
|
+
])
|
|
149
|
+
const value = payload.defaultJSValue()
|
|
7
150
|
|
|
8
|
-
|
|
9
|
-
|
|
10
|
-
|
|
11
|
-
|
|
151
|
+
console.assert(value instanceof Record)
|
|
152
|
+
console.assert(value.count === 0n && value.note === null)
|
|
153
|
+
console.assert(payload.defaultJSHint().constructor instanceof Function)
|
|
154
|
+
console.assert(fields.int32('id').defaultArrowScalar() === 0)
|
|
155
|
+
console.assert(
|
|
156
|
+
fields.uint8('small').toSchemeCompat('spark').dataType.kind === 'int16',
|
|
157
|
+
)
|
|
12
158
|
```
|
|
13
159
|
|
|
14
|
-
|
|
160
|
+
Defaults are computed by the Rust core and projected through the same typed
|
|
161
|
+
path as Record values. Struct defaults remain schema-bound native Records;
|
|
162
|
+
runtime hints use a bounded native constructor category, are frozen and
|
|
163
|
+
cached, and do not materialize a default value or exact Field schema.
|
|
164
|
+
For a Struct Field, that metadata-free hint constructor is a logical layout
|
|
165
|
+
hint through the generic `Record` class, so nested metadata is not exposed by
|
|
166
|
+
the hint. The exact default Record still retains its complete outer Field and
|
|
167
|
+
uses its own generated class. Hint identity is wrapper-local, not a global
|
|
168
|
+
interning promise for equivalent schemas.
|
|
169
|
+
Arrow scalars use one copied one-row IPC projection into Apache Arrow JS, and
|
|
170
|
+
unsupported Arrow JS layouts fail without introducing a second scalar model.
|
|
171
|
+
Run `npm run bench:defaults` for JavaScript defaults, cached hints,
|
|
172
|
+
compatibility normalization, and Arrow-scalar IPC materialization.
|
|
15
173
|
|
|
16
174
|
```javascript
|
|
17
|
-
const {
|
|
175
|
+
const { Field, MediaType, MimeType } = require('yggdryl')
|
|
18
176
|
|
|
19
|
-
const
|
|
20
|
-
|
|
21
|
-
|
|
177
|
+
const media = MediaType.fromParts(
|
|
178
|
+
MimeType.CSV,
|
|
179
|
+
new Set([MimeType.GZIP, MimeType.ZSTD]),
|
|
180
|
+
)
|
|
181
|
+
const field = new Field('payload', 'binary', false, {
|
|
182
|
+
'HTTPS:Content-Type': 'text/csv; charset=utf-8',
|
|
183
|
+
})
|
|
184
|
+
field.setMediaType(media)
|
|
22
185
|
|
|
23
|
-
|
|
24
|
-
console.
|
|
25
|
-
console.
|
|
26
|
-
console.log(url.username) // user
|
|
27
|
-
console.log(url.toString()) // https://user:pw@example.com:8443/api?v=1#top
|
|
186
|
+
console.assert(field.mimeType.equals(MimeType.CSV))
|
|
187
|
+
console.assert(field.contentEncoding === 'gzip, zstd')
|
|
188
|
+
console.assert(field.get('HTTPS:CONTENT-TYPE') === 'text/csv')
|
|
28
189
|
```
|
|
29
190
|
|
|
30
|
-
|
|
191
|
+
`MimeType` exposes every native known value as a frozen class constant and
|
|
192
|
+
accepts custom validated MIME names. `MediaType()` defaults to octet-stream;
|
|
193
|
+
its iterable adapters consume once and `encodings` returns a detached Array.
|
|
194
|
+
HTTP and HTTPS Field input shares canonical lowercase `http:*` Arrow metadata.
|
|
195
|
+
Raw headers preserve parameters, while typed MIME/media, exact unsigned
|
|
196
|
+
content length (`bigint`), and absolute HTTP Location accessors remain native.
|
|
197
|
+
Media pair updates are atomic and cache-aware.
|
|
198
|
+
|
|
199
|
+
```javascript
|
|
200
|
+
const { DataType, Field, fields } = require('yggdryl')
|
|
201
|
+
|
|
202
|
+
const id = fields.int32('id', { nullable: false })
|
|
203
|
+
const tags = fields.list('tags', fields.utf8('item'))
|
|
204
|
+
const row = DataType.fromFields([id, tags])
|
|
205
|
+
|
|
206
|
+
console.assert(id instanceof Field)
|
|
207
|
+
console.assert(tags.dataType.kind === 'list')
|
|
208
|
+
console.assert(row.kind === 'struct')
|
|
209
|
+
console.assert(id.showDiff(id) === '✓ equal')
|
|
210
|
+
console.assert([...id.showDiffs(fields.int64('id'))].length > 0)
|
|
211
|
+
```
|
|
212
|
+
|
|
213
|
+
The `fields` namespace covers every datatype variant and returns the same
|
|
214
|
+
generic native `Field`; TypeScript retains the exact kind/value view. Equality
|
|
215
|
+
can ignore recursive metadata with `equals(other, false)`, while `showDiffs`
|
|
216
|
+
returns a UTF-8 iterator and `showDiff` joins its terminal-readable lines.
|
|
217
|
+
|
|
218
|
+
Finite alternatives can use `DataType.variant(fields)` or
|
|
219
|
+
`fields.variant(name, fields, options)`. Both assign dense Arrow Union type IDs
|
|
220
|
+
in declaration order and retain the ordinary `union` kind; Record values use
|
|
221
|
+
the explicit `{ typeId, value }` shape. Iceberg/Parquet Variant and PostgreSQL
|
|
222
|
+
`json/jsonb` remain explicit adapter formats, not aliases for this tagged Arrow
|
|
223
|
+
layout.
|
|
224
|
+
|
|
225
|
+
```javascript
|
|
226
|
+
const fs = require('node:fs')
|
|
227
|
+
const os = require('node:os')
|
|
228
|
+
const path = require('node:path')
|
|
229
|
+
const arrow = require('apache-arrow')
|
|
230
|
+
const { BatchReader, Field, IOBase, fields, iceberg } = require('yggdryl')
|
|
231
|
+
|
|
232
|
+
// A location is absolute: a handle is a URL, and a relative name names no root.
|
|
233
|
+
const root = fs.mkdtempSync(path.join(os.tmpdir(), 'yggdryl-'))
|
|
234
|
+
|
|
235
|
+
const schema = iceberg.assignFieldIds(
|
|
236
|
+
fields.struct('row', [Field.from('id: int64'), Field.from('venue: utf8')], {
|
|
237
|
+
nullable: false,
|
|
238
|
+
}),
|
|
239
|
+
)
|
|
240
|
+
const rows = new arrow.Table({
|
|
241
|
+
id: arrow.vectorFromArray([1n, 2n], new arrow.Int64()),
|
|
242
|
+
venue: arrow.vectorFromArray(['XNAS', 'XNYS'], new arrow.Utf8()),
|
|
243
|
+
})
|
|
244
|
+
|
|
245
|
+
// A handle reads and writes records through the encoding its name declares.
|
|
246
|
+
const file = new IOBase(path.join(root, 'trades.parquet'))
|
|
247
|
+
file.writeArrowBatchReader(BatchReader.from(rows))
|
|
248
|
+
console.assert(file.readArrowBatchReader().toTable().numRows === 2)
|
|
249
|
+
|
|
250
|
+
// An Iceberg table is a folder, and a folder is all it ever touches.
|
|
251
|
+
const table = iceberg.Table.create(path.join(root, 'trades'), schema, ['venue'])
|
|
252
|
+
table.append(rows)
|
|
253
|
+
console.assert(table.currentSnapshot.operation === 'append')
|
|
254
|
+
console.assert(table.dataFiles().length === 2)
|
|
255
|
+
```
|
|
256
|
+
|
|
257
|
+
`BatchReader` is the one record shape: a read returns one, a write consumes one,
|
|
258
|
+
and each batch crosses as its own Apache Arrow IPC stream, because Arrow JS has
|
|
259
|
+
no C Data consumer. `BatchReader.from` accepts another reader, an Arrow JS
|
|
260
|
+
`Table` or `RecordBatch`, an array of batches, or Arrow IPC bytes. The encoding
|
|
261
|
+
is never an argument: `recordOptions()` derives it from the handle's media type,
|
|
262
|
+
covering Arrow IPC and Apache Parquet.
|
|
263
|
+
|
|
264
|
+
Use the complete [JavaScript guide](https://platob.github.io/yggdryl/extensions/javascript/)
|
|
265
|
+
for schema and identifier APIs, the [Record and Arrow guide](https://platob.github.io/yggdryl/extensions/javascript/records/)
|
|
266
|
+
for typed rows and copied IPC interoperability, and the [codec guide](https://platob.github.io/yggdryl/extensions/javascript/codecs/)
|
|
267
|
+
for safe class registries, generic format inference, and streaming.
|
|
@@ -0,0 +1,133 @@
|
|
|
1
|
+
'use strict'
|
|
2
|
+
|
|
3
|
+
const fs = require('node:fs')
|
|
4
|
+
const os = require('node:os')
|
|
5
|
+
const path = require('node:path')
|
|
6
|
+
const { performance } = require('node:perf_hooks')
|
|
7
|
+
const { Readable, Writable } = require('node:stream')
|
|
8
|
+
const { Value, codec, json, toml, yaml } = require('yggdryl')
|
|
9
|
+
|
|
10
|
+
const value = {
|
|
11
|
+
trades: Array.from({ length: 1_000 }, (_, index) => ({
|
|
12
|
+
id: BigInt(index),
|
|
13
|
+
price: index / 100,
|
|
14
|
+
symbol: `SYM${index % 20}`,
|
|
15
|
+
})),
|
|
16
|
+
}
|
|
17
|
+
const exotic = {
|
|
18
|
+
bytes: Buffer.from([0, 1, 127, 255]),
|
|
19
|
+
map: new Map([[{ venue: 'XPAR' }, new Set([1n, 2n])]]),
|
|
20
|
+
nan: Number.NaN,
|
|
21
|
+
regexp: /a\/b/giu,
|
|
22
|
+
typed: new Uint16Array([0, 65535]),
|
|
23
|
+
}
|
|
24
|
+
// The temporal and decimal boundary is its own cost: each value crosses as
|
|
25
|
+
// parts rather than as one number, and a Date is rebuilt on the way back.
|
|
26
|
+
const temporal = {
|
|
27
|
+
at: Value.timestamp(1700000000000000n, 'us', 'UTC'),
|
|
28
|
+
date: new Date('2026-08-15T12:30:00.000Z'),
|
|
29
|
+
on: Value.date(19723),
|
|
30
|
+
price: Value.decimal(-1050n, 2),
|
|
31
|
+
sinceMidnight: Value.time(45296000000n, 'us'),
|
|
32
|
+
took: Value.duration(90n, 's'),
|
|
33
|
+
}
|
|
34
|
+
let deep = { leaf: true }
|
|
35
|
+
for (let depth = 0; depth < 24; depth += 1) deep = { nested: deep }
|
|
36
|
+
|
|
37
|
+
function measure(name, bytes, iterations, operation) {
|
|
38
|
+
for (let index = 0; index < 5; index += 1) operation()
|
|
39
|
+
const started = performance.now()
|
|
40
|
+
for (let index = 0; index < iterations; index += 1) operation()
|
|
41
|
+
const elapsed = performance.now() - started
|
|
42
|
+
const throughput = (bytes * iterations) / (elapsed / 1_000) / (1024 * 1024)
|
|
43
|
+
console.log(
|
|
44
|
+
`${name}: ${(elapsed / iterations).toFixed(3)} ms/op, ${throughput.toFixed(1)} MiB/s`,
|
|
45
|
+
)
|
|
46
|
+
}
|
|
47
|
+
|
|
48
|
+
async function measureAsync(name, bytes, iterations, operation) {
|
|
49
|
+
for (let index = 0; index < 2; index += 1) await operation()
|
|
50
|
+
const started = performance.now()
|
|
51
|
+
for (let index = 0; index < iterations; index += 1) await operation()
|
|
52
|
+
const elapsed = performance.now() - started
|
|
53
|
+
const throughput = (bytes * iterations) / (elapsed / 1_000) / (1024 * 1024)
|
|
54
|
+
console.log(
|
|
55
|
+
`${name}: ${(elapsed / iterations).toFixed(3)} ms/op, ${throughput.toFixed(1)} MiB/s`,
|
|
56
|
+
)
|
|
57
|
+
}
|
|
58
|
+
|
|
59
|
+
async function main() {
|
|
60
|
+
const directory = fs.mkdtempSync(path.join(os.tmpdir(), 'yggdryl-node-bench-'))
|
|
61
|
+
try {
|
|
62
|
+
for (const [name, format, extension] of [
|
|
63
|
+
['json', json, 'json'],
|
|
64
|
+
['toml', toml, 'toml'],
|
|
65
|
+
['yaml', yaml, 'yaml'],
|
|
66
|
+
]) {
|
|
67
|
+
const encoded = format.dumps(value)
|
|
68
|
+
const text = encoded.toString('utf8')
|
|
69
|
+
const padded = Buffer.concat([Buffer.from('xx'), encoded, Buffer.from('yy')])
|
|
70
|
+
const view = new DataView(
|
|
71
|
+
padded.buffer,
|
|
72
|
+
padded.byteOffset + 2,
|
|
73
|
+
encoded.byteLength,
|
|
74
|
+
)
|
|
75
|
+
const file = path.join(directory, `value.${extension}`)
|
|
76
|
+
fs.writeFileSync(file, encoded)
|
|
77
|
+
|
|
78
|
+
// Keep these group spellings stable so before/after runs remain comparable.
|
|
79
|
+
measure(`${name}/slice`, encoded.length, 100, () => format.loads(encoded))
|
|
80
|
+
measure(`${name}/string`, encoded.length, 100, () => format.loads(text))
|
|
81
|
+
measure(`${name}/offset_view`, encoded.length, 100, () => format.loads(view))
|
|
82
|
+
measure(`${name}/reader_path`, encoded.length, 100, () => format.load(file))
|
|
83
|
+
measure(`${name}/vector_emit`, encoded.length, 100, () => format.dumps(value))
|
|
84
|
+
measure(`${name}/writer_path`, encoded.length, 100, () => format.dump(value, file))
|
|
85
|
+
await measureAsync(`${name}/reader_stream`, encoded.length, 25, () =>
|
|
86
|
+
format.load(Readable.from([encoded])),
|
|
87
|
+
)
|
|
88
|
+
await measureAsync(`${name}/writer_stream`, encoded.length, 25, () =>
|
|
89
|
+
format.dump(
|
|
90
|
+
value,
|
|
91
|
+
new Writable({ write(_chunk, _encoding, done) { done() } }),
|
|
92
|
+
),
|
|
93
|
+
)
|
|
94
|
+
|
|
95
|
+
const exoticEncoded = format.dumps(exotic)
|
|
96
|
+
measure(`${name}/exotic_values`, exoticEncoded.length, 50, () =>
|
|
97
|
+
format.loads(exoticEncoded),
|
|
98
|
+
)
|
|
99
|
+
const temporalEncoded = format.dumps(temporal)
|
|
100
|
+
measure(`${name}/temporal_values`, temporalEncoded.length, 50, () =>
|
|
101
|
+
format.loads(temporalEncoded),
|
|
102
|
+
)
|
|
103
|
+
const deepEncoded = format.dumps(deep)
|
|
104
|
+
measure(`${name}/deep_nested`, deepEncoded.length, 50, () =>
|
|
105
|
+
format.loads(deepEncoded),
|
|
106
|
+
)
|
|
107
|
+
}
|
|
108
|
+
|
|
109
|
+
// The pivot is the conversion every load and dump crosses, measured on its
|
|
110
|
+
// own against the same payload so a codec number can be read against it.
|
|
111
|
+
const pivotBytes = json.dumps(value).length
|
|
112
|
+
measure('pivot/from_js', pivotBytes, 100, () => Value.fromJs(value))
|
|
113
|
+
const pivot = Value.fromJs(value)
|
|
114
|
+
measure('pivot/as_js', pivotBytes, 100, () => pivot.asJs())
|
|
115
|
+
|
|
116
|
+
const inferred = json.dumps(value)
|
|
117
|
+
measure('generic/content_sniff', inferred.length, 100, () => codec.from(inferred))
|
|
118
|
+
measure('generic/explicit_json', inferred.length, 100, () =>
|
|
119
|
+
codec.from(inferred, { format: 'json' }),
|
|
120
|
+
)
|
|
121
|
+
const inferredToml = toml.dumps(value)
|
|
122
|
+
measure('generic/content_infer_toml', inferredToml.length, 50, () =>
|
|
123
|
+
codec.from(inferredToml),
|
|
124
|
+
)
|
|
125
|
+
} finally {
|
|
126
|
+
fs.rmSync(directory, { force: true, recursive: true })
|
|
127
|
+
}
|
|
128
|
+
}
|
|
129
|
+
|
|
130
|
+
main().catch((error) => {
|
|
131
|
+
console.error(error)
|
|
132
|
+
process.exitCode = 1
|
|
133
|
+
})
|