@crewhaus/tool-table 0.7.0 → 0.8.0
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 +201 -0
- package/NOTICE +9 -0
- package/dist/index.js +55 -13
- package/dist/lib/drift.js +12 -5
- package/dist/lib/profile.js +3 -1
- package/dist/paths.d.ts +21 -2
- package/dist/paths.js +72 -13
- package/package.json +13 -8
package/LICENSE
ADDED
|
@@ -0,0 +1,201 @@
|
|
|
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.
|
package/NOTICE
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
1
|
+
CrewHaus Factory
|
|
2
|
+
Copyright 2026 Max Meier
|
|
3
|
+
|
|
4
|
+
This product includes software developed by Max Meier
|
|
5
|
+
(operating as StudioMax — https://studiomax.io) and contributors.
|
|
6
|
+
|
|
7
|
+
The CrewHaus name and logo are trademarks of Max Meier. See
|
|
8
|
+
https://github.com/crewhaus/factory/blob/main/TRADEMARK.md for the
|
|
9
|
+
use-of-marks policy.
|
package/dist/index.js
CHANGED
|
@@ -15,15 +15,22 @@
|
|
|
15
15
|
* repository would disagree about quoting and embedded newlines on the same
|
|
16
16
|
* file, in different tools, which is the worst way to disagree.
|
|
17
17
|
*/
|
|
18
|
-
import { readFileSync, statSync } from "node:fs";
|
|
19
18
|
import { buildTool } from "@crewhaus/tool-builder";
|
|
20
19
|
import { parseCsv } from "@crewhaus/tool-data";
|
|
20
|
+
import { openForReadSync } from "@crewhaus/tool-safety/fs";
|
|
21
21
|
import { z } from "zod";
|
|
22
22
|
import { DriftError, compareDrift } from "./lib/drift";
|
|
23
23
|
import { profileTable } from "./lib/profile";
|
|
24
24
|
import { FIELD_NORMALIZERS, diffTables, linkRecords, normalizeContact, } from "./lib/reconcile";
|
|
25
25
|
import { parseFixedWidth, shardRows, toLong, toWide } from "./lib/reshape";
|
|
26
|
-
import { resolveSafe } from "./paths";
|
|
26
|
+
import { resolveSafe, workspaceRoot } from "./paths";
|
|
27
|
+
/**
|
|
28
|
+
* A file's text as 0.7.0's `readFileSync(path, "utf8")` gave it: a leading
|
|
29
|
+
* byte-order mark kept. tool-safety's `text` drops one, which moved
|
|
30
|
+
* FixedWidthParse's columns by one on a file that starts with one (bounds
|
|
31
|
+
* review). A CSV's header is unaffected: parseCsv drops the mark itself.
|
|
32
|
+
*/
|
|
33
|
+
const KEEP_BOM = new TextDecoder("utf-8", { ignoreBOM: true });
|
|
27
34
|
const json = (value) => JSON.stringify(value);
|
|
28
35
|
const LIMITS = {
|
|
29
36
|
fileBytes: 512 * 1024 * 1024,
|
|
@@ -35,14 +42,36 @@ const LIMITS = {
|
|
|
35
42
|
/** A stored profile is a summary; anything this big is the data by mistake. */
|
|
36
43
|
profileBytes: 64 * 1024 * 1024,
|
|
37
44
|
};
|
|
45
|
+
/**
|
|
46
|
+
* A workspace file's text, at most `maxBytes` of it.
|
|
47
|
+
*
|
|
48
|
+
* Opened without blocking, and only as a regular file: a FIFO with no writer
|
|
49
|
+
* blocks an ordinary open for ever, and these reads were synchronous, so a
|
|
50
|
+
* named pipe in the workspace stopped the whole harness (C074). The limit is
|
|
51
|
+
* enforced while reading; `overLimit` says the file holds more.
|
|
52
|
+
*/
|
|
53
|
+
function readWorkspaceText(tool, file, maxBytes) {
|
|
54
|
+
const read = openForReadSync(workspaceRoot(), file, { maxBytes });
|
|
55
|
+
if (!read.ok)
|
|
56
|
+
throw new Error(`${tool}: ${read.reason}`);
|
|
57
|
+
return {
|
|
58
|
+
// Decoded only when asked for: a caller refuses a file over the limit unread.
|
|
59
|
+
get text() {
|
|
60
|
+
return KEEP_BOM.decode(read.bytes);
|
|
61
|
+
},
|
|
62
|
+
size: read.size,
|
|
63
|
+
overLimit: read.truncated,
|
|
64
|
+
};
|
|
65
|
+
}
|
|
38
66
|
/** Read a delimited file into a header and rows of strings. */
|
|
39
67
|
function readTable(tool, file, options) {
|
|
40
68
|
const at = resolveSafe(tool, file);
|
|
41
|
-
const
|
|
42
|
-
|
|
69
|
+
const read = readWorkspaceText(tool, file, LIMITS.fileBytes);
|
|
70
|
+
const bytes = read.size;
|
|
71
|
+
if (read.overLimit) {
|
|
43
72
|
throw new Error(`${at.rel} is ${bytes} bytes, over the ${LIMITS.fileBytes}-byte limit`);
|
|
44
73
|
}
|
|
45
|
-
const text =
|
|
74
|
+
const text = read.text;
|
|
46
75
|
// `parseCsv` returns every row including the header; splitting it here
|
|
47
76
|
// keeps one reader for the whole repository rather than two that disagree
|
|
48
77
|
// about quoting on the same file.
|
|
@@ -164,13 +193,19 @@ export const tableProfile = buildTool({
|
|
|
164
193
|
*/
|
|
165
194
|
function loadReferenceProfile(file) {
|
|
166
195
|
const at = resolveSafe("DataDriftCheck", file);
|
|
167
|
-
|
|
168
|
-
|
|
169
|
-
|
|
196
|
+
let read;
|
|
197
|
+
try {
|
|
198
|
+
read = readWorkspaceText("DataDriftCheck", file, LIMITS.profileBytes);
|
|
199
|
+
}
|
|
200
|
+
catch (err) {
|
|
201
|
+
return err.message;
|
|
202
|
+
}
|
|
203
|
+
if (read.overLimit) {
|
|
204
|
+
return `${at.rel} is ${read.size} bytes, far larger than any profile — this is probably not a stored TableProfile`;
|
|
170
205
|
}
|
|
171
206
|
let parsed;
|
|
172
207
|
try {
|
|
173
|
-
parsed = JSON.parse(
|
|
208
|
+
parsed = JSON.parse(read.text);
|
|
174
209
|
}
|
|
175
210
|
catch (err) {
|
|
176
211
|
return `${at.rel} is not JSON: ${err.message}. referenceProfile takes a stored TableProfile result; for raw data use referenceFile`;
|
|
@@ -244,6 +279,13 @@ function columnProblem(value) {
|
|
|
244
279
|
if (typeof counts !== "object" || counts === null || Array.isArray(counts)) {
|
|
245
280
|
return `${label} has a categorical capture with no valueCounts map`;
|
|
246
281
|
}
|
|
282
|
+
// A count the chi-square adds up. A hand-edited "50" would concatenate
|
|
283
|
+
// instead of adding, and the category would drop out of the test.
|
|
284
|
+
for (const [value, count] of Object.entries(counts)) {
|
|
285
|
+
if (typeof count !== "number" || !Number.isFinite(count) || count < 0) {
|
|
286
|
+
return `${label} has a non-numeric count for the value ${JSON.stringify(value)} in its valueCounts; it has been edited by hand and cannot be used as a baseline`;
|
|
287
|
+
}
|
|
288
|
+
}
|
|
247
289
|
return null;
|
|
248
290
|
}
|
|
249
291
|
return `${label} has a drift capture of unknown kind ${JSON.stringify(capture["kind"])}`;
|
|
@@ -682,11 +724,11 @@ export const fixedWidthParse = buildTool({
|
|
|
682
724
|
concurrencySafe: true,
|
|
683
725
|
execute: async (input) => {
|
|
684
726
|
const at = resolveSafe("FixedWidthParse", input.file);
|
|
685
|
-
const
|
|
686
|
-
if (
|
|
687
|
-
throw new Error(`${at.rel} is ${
|
|
727
|
+
const read = readWorkspaceText("FixedWidthParse", input.file, LIMITS.fileBytes);
|
|
728
|
+
if (read.overLimit) {
|
|
729
|
+
throw new Error(`${at.rel} is ${read.size} bytes, over the ${LIMITS.fileBytes}-byte limit`);
|
|
688
730
|
}
|
|
689
|
-
const result = parseFixedWidth(
|
|
731
|
+
const result = parseFixedWidth(read.text, input.fields, {
|
|
690
732
|
skipLines: input.skipLines,
|
|
691
733
|
});
|
|
692
734
|
const limit = input.limit ?? 500;
|
package/dist/lib/drift.js
CHANGED
|
@@ -127,17 +127,24 @@ export function chiSquareUpperTail(x, df) {
|
|
|
127
127
|
* move a verdict. A caller gating on `p` should gate on this first.
|
|
128
128
|
*/
|
|
129
129
|
export function chiSquareHomogeneity(reference, current) {
|
|
130
|
+
// Own properties only. The keys are CELL VALUES, and a stored profile comes
|
|
131
|
+
// back from JSON.parse as a plain object: `reference["constructor"]` on a
|
|
132
|
+
// reference that never saw that value is Object's constructor, a function,
|
|
133
|
+
// and `function + 80` is a string that compares false against 0 — so a
|
|
134
|
+
// brand-new category named "constructor", "toString" or "__proto__"
|
|
135
|
+
// vanished from the table and the test answered p = 1 on real drift.
|
|
136
|
+
const countOf = (counts, key) => Object.hasOwn(counts, key) ? counts[key] : 0;
|
|
130
137
|
// A key recorded as zero on BOTH sides is dropped rather than counted: it
|
|
131
138
|
// would make its column total zero, so both its expected counts would be
|
|
132
139
|
// 0/0, and it would inflate df with a cell that holds no observation.
|
|
133
140
|
const categories = [...new Set([...Object.keys(reference), ...Object.keys(current)])]
|
|
134
|
-
.filter((key) => (reference
|
|
141
|
+
.filter((key) => countOf(reference, key) + countOf(current, key) > 0)
|
|
135
142
|
.sort();
|
|
136
143
|
let referenceTotal = 0;
|
|
137
144
|
let currentTotal = 0;
|
|
138
145
|
for (const key of categories) {
|
|
139
|
-
referenceTotal += reference
|
|
140
|
-
currentTotal += current
|
|
146
|
+
referenceTotal += countOf(reference, key);
|
|
147
|
+
currentTotal += countOf(current, key);
|
|
141
148
|
}
|
|
142
149
|
const total = referenceTotal + currentTotal;
|
|
143
150
|
const base = {
|
|
@@ -171,8 +178,8 @@ export function chiSquareHomogeneity(reference, current) {
|
|
|
171
178
|
let cellsBelowFive = 0;
|
|
172
179
|
let cellsBelowOne = 0;
|
|
173
180
|
for (const key of categories) {
|
|
174
|
-
const observedReference = reference
|
|
175
|
-
const observedCurrent = current
|
|
181
|
+
const observedReference = countOf(reference, key);
|
|
182
|
+
const observedCurrent = countOf(current, key);
|
|
176
183
|
const columnTotal = observedReference + observedCurrent;
|
|
177
184
|
// A column total of zero cannot occur: the key is in the union because at
|
|
178
185
|
// least one side counted it. So neither expectation below is 0/0.
|
package/dist/lib/profile.js
CHANGED
|
@@ -314,7 +314,9 @@ function captureColumn(numericValues, ordered, nonNull, settings) {
|
|
|
314
314
|
// `otherCount` still says zero, so the capture claims a complete category
|
|
315
315
|
// list that is missing a category — and a value arriving for the first time
|
|
316
316
|
// today is never named as new. A null prototype makes it an ordinary key,
|
|
317
|
-
// and `JSON.stringify`/`JSON.parse` round-trip
|
|
317
|
+
// and `JSON.stringify`/`JSON.parse` round-trip the keys intact — though
|
|
318
|
+
// the parsed map is a plain object again, which is why the chi-square
|
|
319
|
+
// (drift.ts) reads own properties only.
|
|
318
320
|
const valueCounts = Object.create(null);
|
|
319
321
|
for (const { value, count } of kept)
|
|
320
322
|
valueCounts[value] = count;
|
package/dist/paths.d.ts
CHANGED
|
@@ -1,10 +1,29 @@
|
|
|
1
1
|
import { CrewhausError } from "@crewhaus/errors";
|
|
2
|
-
/**
|
|
2
|
+
/**
|
|
3
|
+
* The longest path this resolves, in UTF-16 code units; a longer one is
|
|
4
|
+
* refused before it is walked. Nothing that long can be opened or created:
|
|
5
|
+
* PATH_MAX is 1,024 bytes on macOS and 4,096 on Linux, Windows stops at
|
|
6
|
+
* 32,767 UTF-16 units, and a path's UTF-8 form is never shorter than its
|
|
7
|
+
* UTF-16 one. The limit is twice that because the part of a path that exists
|
|
8
|
+
* is itself under PATH_MAX, so the part that does not is over PATH_MAX on its
|
|
9
|
+
* own: no spelling of the place reaches it, not even one through a symlink
|
|
10
|
+
* that shortens the part that exists.
|
|
11
|
+
*/
|
|
12
|
+
export declare const MAX_PATH_CHARS: number;
|
|
13
|
+
/**
|
|
14
|
+
* Raised when a caller-supplied path resolves outside the workspace root, or
|
|
15
|
+
* is longer than any path can be.
|
|
16
|
+
*/
|
|
3
17
|
export declare class ToolPermissionError extends CrewhausError {
|
|
4
18
|
readonly name = "ToolPermissionError";
|
|
5
19
|
readonly toolName: string;
|
|
6
20
|
readonly path: string;
|
|
7
|
-
|
|
21
|
+
/**
|
|
22
|
+
* Why, when it is not that the location escapes the workspace root: a path
|
|
23
|
+
* longer than any path can be. A caller that rewords the refusal says this.
|
|
24
|
+
*/
|
|
25
|
+
readonly reason: string | undefined;
|
|
26
|
+
constructor(toolName: string, attemptedPath: string, reason?: string);
|
|
8
27
|
}
|
|
9
28
|
/**
|
|
10
29
|
* A validated path, in both forms the tools need.
|
package/dist/paths.js
CHANGED
|
@@ -11,15 +11,45 @@
|
|
|
11
11
|
import { lstatSync, readlinkSync, realpathSync } from "node:fs";
|
|
12
12
|
import * as path from "node:path";
|
|
13
13
|
import { CrewhausError } from "@crewhaus/errors";
|
|
14
|
-
/**
|
|
14
|
+
/**
|
|
15
|
+
* The longest path this resolves, in UTF-16 code units; a longer one is
|
|
16
|
+
* refused before it is walked. Nothing that long can be opened or created:
|
|
17
|
+
* PATH_MAX is 1,024 bytes on macOS and 4,096 on Linux, Windows stops at
|
|
18
|
+
* 32,767 UTF-16 units, and a path's UTF-8 form is never shorter than its
|
|
19
|
+
* UTF-16 one. The limit is twice that because the part of a path that exists
|
|
20
|
+
* is itself under PATH_MAX, so the part that does not is over PATH_MAX on its
|
|
21
|
+
* own: no spelling of the place reaches it, not even one through a symlink
|
|
22
|
+
* that shortens the part that exists.
|
|
23
|
+
*/
|
|
24
|
+
export const MAX_PATH_CHARS = 2 * (process.platform === "darwin" ? 1_024 : process.platform === "win32" ? 32_767 : 4_096);
|
|
25
|
+
/** A path as a refusal quotes it: whole, unless it is past {@link MAX_PATH_CHARS}. */
|
|
26
|
+
function shownPath(given) {
|
|
27
|
+
return given.length > MAX_PATH_CHARS ? `${given.slice(0, 64)}…` : given;
|
|
28
|
+
}
|
|
29
|
+
/** Why a path past {@link MAX_PATH_CHARS} is refused: its length and the limit. */
|
|
30
|
+
function tooLong(abs) {
|
|
31
|
+
return `it is ${abs.length} characters once resolved, over the ${MAX_PATH_CHARS}-character limit: no path that long can be opened or created`;
|
|
32
|
+
}
|
|
33
|
+
/**
|
|
34
|
+
* Raised when a caller-supplied path resolves outside the workspace root, or
|
|
35
|
+
* is longer than any path can be.
|
|
36
|
+
*/
|
|
15
37
|
export class ToolPermissionError extends CrewhausError {
|
|
16
38
|
name = "ToolPermissionError";
|
|
17
39
|
toolName;
|
|
18
40
|
path;
|
|
19
|
-
|
|
20
|
-
|
|
41
|
+
/**
|
|
42
|
+
* Why, when it is not that the location escapes the workspace root: a path
|
|
43
|
+
* longer than any path can be. A caller that rewords the refusal says this.
|
|
44
|
+
*/
|
|
45
|
+
reason;
|
|
46
|
+
constructor(toolName, attemptedPath, reason) {
|
|
47
|
+
super("tool", reason === undefined
|
|
48
|
+
? `tool "${toolName}" rejected path "${attemptedPath}": resolved location escapes the workspace root`
|
|
49
|
+
: `tool "${toolName}" rejected path "${shownPath(attemptedPath)}": ${reason}`);
|
|
21
50
|
this.toolName = toolName;
|
|
22
51
|
this.path = attemptedPath;
|
|
52
|
+
this.reason = reason;
|
|
23
53
|
}
|
|
24
54
|
}
|
|
25
55
|
/** The workspace root, resolved. Every path is contained within it. */
|
|
@@ -67,15 +97,7 @@ function nameExists(p) {
|
|
|
67
97
|
function resolveLocation(target, depth = 0) {
|
|
68
98
|
if (depth > 40)
|
|
69
99
|
throw new Error(`symlink chain at "${target}" is too long to resolve`);
|
|
70
|
-
|
|
71
|
-
const tail = [];
|
|
72
|
-
while (!nameExists(probe)) {
|
|
73
|
-
tail.unshift(path.basename(probe));
|
|
74
|
-
const parent = path.dirname(probe);
|
|
75
|
-
if (parent === probe)
|
|
76
|
-
break; // reached the filesystem root
|
|
77
|
-
probe = parent;
|
|
78
|
-
}
|
|
100
|
+
const { probe, tail } = deepestName(target);
|
|
79
101
|
let probeReal;
|
|
80
102
|
try {
|
|
81
103
|
probeReal = realpathSync(probe);
|
|
@@ -97,7 +119,41 @@ function resolveLocation(target, depth = 0) {
|
|
|
97
119
|
const base = realpathSync(path.dirname(probe));
|
|
98
120
|
probeReal = resolveLocation(path.resolve(base, link), depth + 1);
|
|
99
121
|
}
|
|
100
|
-
|
|
122
|
+
// One string, not one argument per name: Bun's `path.join` keeps only
|
|
123
|
+
// (argument count mod 65,536) of its arguments.
|
|
124
|
+
return tail.length > 0 ? path.join(probeReal, tail) : probeReal;
|
|
125
|
+
}
|
|
126
|
+
/**
|
|
127
|
+
* `target`, an absolute path, split where its deepest prefix that exists as
|
|
128
|
+
* a NAME ends: that prefix, and the names below it, which do not exist, as
|
|
129
|
+
* one string ("" when `target` itself exists). This is `path.dirname` and
|
|
130
|
+
* `path.basename` worked by index on `target` itself: handing them each
|
|
131
|
+
* shorter prefix in turn copied the rest of the path once per missing name,
|
|
132
|
+
* the square of a count the caller picks.
|
|
133
|
+
*/
|
|
134
|
+
function deepestName(target) {
|
|
135
|
+
const top = path.parse(target).root.length;
|
|
136
|
+
const isSep = (i) => target[i] === "/" || target[i] === path.sep;
|
|
137
|
+
let probe = target;
|
|
138
|
+
let start = target.length;
|
|
139
|
+
let stop = -1;
|
|
140
|
+
while (!nameExists(probe)) {
|
|
141
|
+
// `path.basename(probe)` is `target.slice(start, end)`, and
|
|
142
|
+
// `path.dirname(probe)` is `target.slice(0, up)`.
|
|
143
|
+
let end = probe.length;
|
|
144
|
+
while (end > top && isSep(end - 1))
|
|
145
|
+
end--;
|
|
146
|
+
if (stop < 0)
|
|
147
|
+
stop = end;
|
|
148
|
+
start = end;
|
|
149
|
+
while (start > top && !isSep(start - 1))
|
|
150
|
+
start--;
|
|
151
|
+
const up = start > top ? start - 1 : top;
|
|
152
|
+
if (up === probe.length)
|
|
153
|
+
break; // reached the filesystem root
|
|
154
|
+
probe = target.slice(0, up);
|
|
155
|
+
}
|
|
156
|
+
return { probe, tail: stop < 0 ? "" : target.slice(start, stop) };
|
|
101
157
|
}
|
|
102
158
|
export function resolveSafe(toolName, rel, root = workspaceRoot()) {
|
|
103
159
|
const rootResolved = path.resolve(root);
|
|
@@ -107,6 +163,9 @@ export function resolveSafe(toolName, rel, root = workspaceRoot()) {
|
|
|
107
163
|
if (abs !== rootResolved && !abs.startsWith(`${rootResolved}${path.sep}`)) {
|
|
108
164
|
throw new ToolPermissionError(toolName, rel);
|
|
109
165
|
}
|
|
166
|
+
// Longer than any path can be: refused before the walk below reads it.
|
|
167
|
+
if (abs.length > MAX_PATH_CHARS)
|
|
168
|
+
throw new ToolPermissionError(toolName, rel, tooLong(abs));
|
|
110
169
|
let real;
|
|
111
170
|
try {
|
|
112
171
|
const rootReal = realpathSync(rootResolved);
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@crewhaus/tool-table",
|
|
3
|
-
"version": "0.
|
|
3
|
+
"version": "0.8.0",
|
|
4
4
|
"type": "module",
|
|
5
5
|
"description": "Deterministic tabular tools: profiling, drift detection, keyed reconciliation, record linkage, contact normalization, reshaping, sharding and fixed-width parsing",
|
|
6
6
|
"main": "dist/index.js",
|
|
@@ -8,18 +8,20 @@
|
|
|
8
8
|
"exports": {
|
|
9
9
|
".": {
|
|
10
10
|
"types": "./dist/index.d.ts",
|
|
11
|
-
"import": "./dist/index.js"
|
|
11
|
+
"import": "./dist/index.js",
|
|
12
|
+
"default": "./dist/index.js"
|
|
12
13
|
}
|
|
13
14
|
},
|
|
14
15
|
"scripts": {
|
|
15
16
|
"test": "bun test src"
|
|
16
17
|
},
|
|
17
18
|
"dependencies": {
|
|
18
|
-
"@crewhaus/errors": "0.
|
|
19
|
-
"@crewhaus/tool-builder": "0.
|
|
20
|
-
"@crewhaus/tool-catalog": "0.
|
|
21
|
-
"@crewhaus/tool-data": "0.
|
|
22
|
-
"@crewhaus/tool-math": "0.
|
|
19
|
+
"@crewhaus/errors": "0.8.0",
|
|
20
|
+
"@crewhaus/tool-builder": "0.8.0",
|
|
21
|
+
"@crewhaus/tool-catalog": "0.8.0",
|
|
22
|
+
"@crewhaus/tool-data": "0.8.0",
|
|
23
|
+
"@crewhaus/tool-math": "0.8.0",
|
|
24
|
+
"@crewhaus/tool-safety": "0.8.0",
|
|
23
25
|
"zod": "^3.23.8"
|
|
24
26
|
},
|
|
25
27
|
"devDependencies": {
|
|
@@ -43,5 +45,8 @@
|
|
|
43
45
|
"publishConfig": {
|
|
44
46
|
"access": "public"
|
|
45
47
|
},
|
|
46
|
-
"files": ["dist", "README.md", "LICENSE", "NOTICE"]
|
|
48
|
+
"files": ["dist", "README.md", "LICENSE", "NOTICE"],
|
|
49
|
+
"engines": {
|
|
50
|
+
"bun": ">=1.3.14"
|
|
51
|
+
}
|
|
47
52
|
}
|