rowpipe 1.0.0 → 1.2.0
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/README.md +327 -41
- package/dist/cli/commands/diff.d.ts +30 -0
- package/dist/cli/commands/diff.d.ts.map +1 -0
- package/dist/cli/commands/diff.js +143 -0
- package/dist/cli/commands/diff.js.map +1 -0
- package/dist/cli/commands/files.d.ts +35 -0
- package/dist/cli/commands/files.d.ts.map +1 -0
- package/dist/cli/commands/files.js +93 -0
- package/dist/cli/commands/files.js.map +1 -0
- package/dist/cli/index.js +89 -5
- package/dist/cli/index.js.map +1 -1
- package/dist/core/errors.d.ts +23 -0
- package/dist/core/errors.d.ts.map +1 -1
- package/dist/core/errors.js +38 -0
- package/dist/core/errors.js.map +1 -1
- package/dist/core/types.d.ts +4 -0
- package/dist/core/types.d.ts.map +1 -1
- package/dist/diff/comparator.d.ts +17 -0
- package/dist/diff/comparator.d.ts.map +1 -0
- package/dist/diff/comparator.js +158 -0
- package/dist/diff/comparator.js.map +1 -0
- package/dist/diff/engine.d.ts +10 -0
- package/dist/diff/engine.d.ts.map +1 -0
- package/dist/diff/engine.js +333 -0
- package/dist/diff/engine.js.map +1 -0
- package/dist/diff/hash.d.ts +6 -0
- package/dist/diff/hash.d.ts.map +1 -0
- package/dist/diff/hash.js +50 -0
- package/dist/diff/hash.js.map +1 -0
- package/dist/diff/key.d.ts +21 -0
- package/dist/diff/key.d.ts.map +1 -0
- package/dist/diff/key.js +107 -0
- package/dist/diff/key.js.map +1 -0
- package/dist/diff/reporter.d.ts +18 -0
- package/dist/diff/reporter.d.ts.map +1 -0
- package/dist/diff/reporter.js +133 -0
- package/dist/diff/reporter.js.map +1 -0
- package/dist/diff/schema.d.ts +7 -0
- package/dist/diff/schema.d.ts.map +1 -0
- package/dist/diff/schema.js +65 -0
- package/dist/diff/schema.js.map +1 -0
- package/dist/diff/storage/disk-index.d.ts +28 -0
- package/dist/diff/storage/disk-index.d.ts.map +1 -0
- package/dist/diff/storage/disk-index.js +105 -0
- package/dist/diff/storage/disk-index.js.map +1 -0
- package/dist/diff/storage/memory-index.d.ts +23 -0
- package/dist/diff/storage/memory-index.d.ts.map +1 -0
- package/dist/diff/storage/memory-index.js +69 -0
- package/dist/diff/storage/memory-index.js.map +1 -0
- package/dist/diff/storage/spillable-index.d.ts +30 -0
- package/dist/diff/storage/spillable-index.d.ts.map +1 -0
- package/dist/diff/storage/spillable-index.js +108 -0
- package/dist/diff/storage/spillable-index.js.map +1 -0
- package/dist/diff/types.d.ts +127 -0
- package/dist/diff/types.d.ts.map +1 -0
- package/dist/diff/types.js +2 -0
- package/dist/diff/types.js.map +1 -0
- package/dist/files/glob.d.ts +21 -0
- package/dist/files/glob.d.ts.map +1 -0
- package/dist/files/glob.js +132 -0
- package/dist/files/glob.js.map +1 -0
- package/dist/files/hash.d.ts +10 -0
- package/dist/files/hash.d.ts.map +1 -0
- package/dist/files/hash.js +67 -0
- package/dist/files/hash.js.map +1 -0
- package/dist/files/index.d.ts +6 -0
- package/dist/files/index.d.ts.map +1 -0
- package/dist/files/index.js +6 -0
- package/dist/files/index.js.map +1 -0
- package/dist/files/mime.d.ts +9 -0
- package/dist/files/mime.d.ts.map +1 -0
- package/dist/files/mime.js +128 -0
- package/dist/files/mime.js.map +1 -0
- package/dist/files/reader.d.ts +19 -0
- package/dist/files/reader.d.ts.map +1 -0
- package/dist/files/reader.js +344 -0
- package/dist/files/reader.js.map +1 -0
- package/dist/files/types.d.ts +47 -0
- package/dist/files/types.d.ts.map +1 -0
- package/dist/files/types.js +2 -0
- package/dist/files/types.js.map +1 -0
- package/dist/index.d.ts +17 -2
- package/dist/index.d.ts.map +1 -1
- package/dist/index.js +19 -2
- package/dist/index.js.map +1 -1
- package/dist/readers/csv.d.ts.map +1 -1
- package/dist/readers/csv.js +59 -27
- package/dist/readers/csv.js.map +1 -1
- package/dist/readers/index.d.ts +2 -0
- package/dist/readers/index.d.ts.map +1 -1
- package/dist/readers/index.js +57 -3
- package/dist/readers/index.js.map +1 -1
- package/dist/readers/json.d.ts.map +1 -1
- package/dist/readers/json.js +6 -8
- package/dist/readers/json.js.map +1 -1
- package/dist/readers/jsonl.d.ts.map +1 -1
- package/dist/readers/jsonl.js +5 -7
- package/dist/readers/jsonl.js.map +1 -1
- package/dist/readers/parquet.d.ts +17 -0
- package/dist/readers/parquet.d.ts.map +1 -0
- package/dist/readers/parquet.js +146 -0
- package/dist/readers/parquet.js.map +1 -0
- package/dist/transforms/expression.d.ts.map +1 -1
- package/dist/transforms/expression.js +73 -7
- package/dist/transforms/expression.js.map +1 -1
- package/dist/utils/compression.d.ts +30 -6
- package/dist/utils/compression.d.ts.map +1 -1
- package/dist/utils/compression.js +95 -18
- package/dist/utils/compression.js.map +1 -1
- package/dist/writers/csv.d.ts.map +1 -1
- package/dist/writers/csv.js +29 -17
- package/dist/writers/csv.js.map +1 -1
- package/dist/writers/index.d.ts +2 -0
- package/dist/writers/index.d.ts.map +1 -1
- package/dist/writers/index.js +49 -4
- package/dist/writers/index.js.map +1 -1
- package/dist/writers/json.d.ts +1 -1
- package/dist/writers/json.d.ts.map +1 -1
- package/dist/writers/json.js +9 -11
- package/dist/writers/json.js.map +1 -1
- package/dist/writers/jsonl.d.ts +1 -1
- package/dist/writers/jsonl.d.ts.map +1 -1
- package/dist/writers/jsonl.js +9 -11
- package/dist/writers/jsonl.js.map +1 -1
- package/dist/writers/markdown.d.ts +21 -0
- package/dist/writers/markdown.d.ts.map +1 -0
- package/dist/writers/markdown.js +82 -0
- package/dist/writers/markdown.js.map +1 -0
- package/dist/writers/parquet.d.ts +19 -0
- package/dist/writers/parquet.d.ts.map +1 -0
- package/dist/writers/parquet.js +129 -0
- package/dist/writers/parquet.js.map +1 -0
- package/package.json +16 -3
- package/skills/rowpipe/SKILL.md +263 -0
- package/benchmarks/memory-bench.ts +0 -109
- package/src/analytics/reduce.ts +0 -388
- package/src/analytics/schema-inference.ts +0 -217
- package/src/analytics/semantic-types.ts +0 -36
- package/src/analytics/stats.ts +0 -383
- package/src/analytics/validator.ts +0 -134
- package/src/cli/commands/cast.ts +0 -60
- package/src/cli/commands/convert.ts +0 -128
- package/src/cli/commands/filter.ts +0 -58
- package/src/cli/commands/inspect.ts +0 -193
- package/src/cli/commands/map.ts +0 -66
- package/src/cli/commands/reduce.ts +0 -74
- package/src/cli/commands/rename.ts +0 -59
- package/src/cli/commands/sample.ts +0 -61
- package/src/cli/commands/schema.ts +0 -86
- package/src/cli/commands/select.ts +0 -59
- package/src/cli/commands/stats.ts +0 -100
- package/src/cli/commands/validate.ts +0 -123
- package/src/cli/index.ts +0 -285
- package/src/core/batch.ts +0 -81
- package/src/core/errors.ts +0 -81
- package/src/core/pipeline.ts +0 -150
- package/src/core/types.ts +0 -110
- package/src/index.ts +0 -52
- package/src/readers/csv.ts +0 -302
- package/src/readers/index.ts +0 -88
- package/src/readers/json.ts +0 -256
- package/src/readers/jsonl.ts +0 -126
- package/src/readers/xlsx.ts +0 -182
- package/src/transforms/cast.ts +0 -212
- package/src/transforms/expression.ts +0 -1114
- package/src/transforms/filter.ts +0 -38
- package/src/transforms/map.ts +0 -99
- package/src/transforms/rename.ts +0 -47
- package/src/transforms/sample.ts +0 -57
- package/src/transforms/select.ts +0 -64
- package/src/utils/compression.ts +0 -43
- package/src/utils/formatting.ts +0 -75
- package/src/utils/progress.ts +0 -37
- package/src/writers/csv.ts +0 -106
- package/src/writers/index.ts +0 -87
- package/src/writers/json.ts +0 -52
- package/src/writers/jsonl.ts +0 -49
- package/src/writers/xlsx.ts +0 -87
- package/tests/analytics.test.ts +0 -119
- package/tests/cli-integration.test.ts +0 -187
- package/tests/map-reduce.test.ts +0 -223
- package/tests/readers-writers.test.ts +0 -189
- package/tests/transforms.test.ts +0 -199
- package/tsconfig.json +0 -21
- package/vitest.config.ts +0 -9
|
@@ -1,58 +0,0 @@
|
|
|
1
|
-
import { createPipeline } from "../../core/pipeline.js";
|
|
2
|
-
import { createReader, inferFormatFromPath as inferReaderFormat } from "../../readers/index.js";
|
|
3
|
-
import { createWriter } from "../../writers/index.js";
|
|
4
|
-
import { filterRows } from "../../transforms/filter.js";
|
|
5
|
-
import { openReadableStream } from "../../utils/compression.js";
|
|
6
|
-
import { logMemoryDebug } from "../../utils/formatting.js";
|
|
7
|
-
import { ProgressReporter } from "../../utils/progress.js";
|
|
8
|
-
|
|
9
|
-
export interface FilterCommandOptions {
|
|
10
|
-
from?: string;
|
|
11
|
-
to?: string;
|
|
12
|
-
sheet?: string;
|
|
13
|
-
delimiter?: string;
|
|
14
|
-
batchSize?: string | number;
|
|
15
|
-
quiet?: boolean;
|
|
16
|
-
noProgress?: boolean;
|
|
17
|
-
}
|
|
18
|
-
|
|
19
|
-
export async function filterCommand(
|
|
20
|
-
inputPath = "-",
|
|
21
|
-
expression: string,
|
|
22
|
-
options: FilterCommandOptions = {}
|
|
23
|
-
): Promise<void> {
|
|
24
|
-
const effectiveBatchSize = Number(options.batchSize) || 1000;
|
|
25
|
-
const progress = new ProgressReporter(options);
|
|
26
|
-
|
|
27
|
-
let fromFormat = options.from?.toLowerCase();
|
|
28
|
-
if (!fromFormat && inputPath !== "-") {
|
|
29
|
-
fromFormat = inferReaderFormat(inputPath) ?? undefined;
|
|
30
|
-
}
|
|
31
|
-
if (!fromFormat) {
|
|
32
|
-
fromFormat = "csv";
|
|
33
|
-
}
|
|
34
|
-
|
|
35
|
-
const toFormat = options.to?.toLowerCase() || (fromFormat === "xlsx" ? "csv" : fromFormat);
|
|
36
|
-
|
|
37
|
-
const inputStream = openReadableStream(inputPath);
|
|
38
|
-
const reader = createReader(inputStream, {
|
|
39
|
-
format: fromFormat,
|
|
40
|
-
sheet: options.sheet,
|
|
41
|
-
delimiter: options.delimiter,
|
|
42
|
-
batchSize: effectiveBatchSize,
|
|
43
|
-
filePath: inputPath,
|
|
44
|
-
});
|
|
45
|
-
|
|
46
|
-
const writer = createWriter(process.stdout, {
|
|
47
|
-
format: toFormat,
|
|
48
|
-
delimiter: options.delimiter,
|
|
49
|
-
});
|
|
50
|
-
|
|
51
|
-
const pipeline = createPipeline(reader, { batchSize: effectiveBatchSize });
|
|
52
|
-
pipeline.pipe(filterRows(expression));
|
|
53
|
-
pipeline.onProgress((info) => progress.update(info));
|
|
54
|
-
|
|
55
|
-
await pipeline.to(writer);
|
|
56
|
-
progress.done();
|
|
57
|
-
logMemoryDebug();
|
|
58
|
-
}
|
|
@@ -1,193 +0,0 @@
|
|
|
1
|
-
import { stat } from "node:fs/promises";
|
|
2
|
-
import { DatasetStatsAggregator } from "../../analytics/stats.js";
|
|
3
|
-
import { SchemaInferenceAggregator } from "../../analytics/schema-inference.js";
|
|
4
|
-
import { InvalidArgumentError } from "../../core/errors.js";
|
|
5
|
-
import { createPipeline } from "../../core/pipeline.js";
|
|
6
|
-
import { createReader, inferFormatFromPath } from "../../readers/index.js";
|
|
7
|
-
import { openReadableStream } from "../../utils/compression.js";
|
|
8
|
-
import {
|
|
9
|
-
formatBytes,
|
|
10
|
-
formatDecimal,
|
|
11
|
-
formatNumber,
|
|
12
|
-
formatTable,
|
|
13
|
-
logMemoryDebug,
|
|
14
|
-
} from "../../utils/formatting.js";
|
|
15
|
-
import { ProgressReporter } from "../../utils/progress.js";
|
|
16
|
-
|
|
17
|
-
export interface InspectCommandOptions {
|
|
18
|
-
sheet?: string;
|
|
19
|
-
path?: string;
|
|
20
|
-
delimiter?: string;
|
|
21
|
-
json?: boolean;
|
|
22
|
-
quiet?: boolean;
|
|
23
|
-
noProgress?: boolean;
|
|
24
|
-
}
|
|
25
|
-
|
|
26
|
-
export async function inspectCommand(
|
|
27
|
-
inputPath = "-",
|
|
28
|
-
options: InspectCommandOptions = {}
|
|
29
|
-
): Promise<void> {
|
|
30
|
-
const progress = new ProgressReporter(options);
|
|
31
|
-
|
|
32
|
-
let fileSize: number | undefined;
|
|
33
|
-
if (inputPath !== "-") {
|
|
34
|
-
try {
|
|
35
|
-
const fileStat = await stat(inputPath);
|
|
36
|
-
fileSize = fileStat.size;
|
|
37
|
-
} catch {
|
|
38
|
-
// Ignore if cannot stat
|
|
39
|
-
}
|
|
40
|
-
}
|
|
41
|
-
|
|
42
|
-
const format =
|
|
43
|
-
inputPath !== "-" ? inferFormatFromPath(inputPath) || "CSV" : "CSV";
|
|
44
|
-
|
|
45
|
-
const stream = openReadableStream(inputPath);
|
|
46
|
-
const reader = createReader(stream, {
|
|
47
|
-
format,
|
|
48
|
-
sheet: options.sheet,
|
|
49
|
-
path: options.path,
|
|
50
|
-
delimiter: options.delimiter,
|
|
51
|
-
filePath: inputPath,
|
|
52
|
-
});
|
|
53
|
-
|
|
54
|
-
// If XLSX without a specific --sheet requested, show rich workbook & sheet breakdown
|
|
55
|
-
if (format === "xlsx" && !options.sheet && reader.inspect) {
|
|
56
|
-
const meta = await reader.inspect();
|
|
57
|
-
if (options.json) {
|
|
58
|
-
process.stdout.write(
|
|
59
|
-
JSON.stringify(
|
|
60
|
-
{
|
|
61
|
-
file: inputPath === "-" ? "stdin" : inputPath,
|
|
62
|
-
format: "XLSX",
|
|
63
|
-
sizeBytes: fileSize,
|
|
64
|
-
sizeFormatted: fileSize !== undefined ? formatBytes(fileSize) : undefined,
|
|
65
|
-
sheetsCount: meta.sheets?.length ?? 0,
|
|
66
|
-
sheets: meta.sheets,
|
|
67
|
-
},
|
|
68
|
-
null,
|
|
69
|
-
2
|
|
70
|
-
) + "\n"
|
|
71
|
-
);
|
|
72
|
-
logMemoryDebug();
|
|
73
|
-
return;
|
|
74
|
-
}
|
|
75
|
-
|
|
76
|
-
process.stdout.write(`File: ${inputPath === "-" ? "stdin" : inputPath}\n`);
|
|
77
|
-
process.stdout.write(`Format: XLSX\n`);
|
|
78
|
-
if (fileSize !== undefined) {
|
|
79
|
-
process.stdout.write(`Size: ${formatBytes(fileSize)}\n`);
|
|
80
|
-
}
|
|
81
|
-
|
|
82
|
-
if (meta.sheets && meta.sheets.length > 0) {
|
|
83
|
-
process.stdout.write(`Sheets: ${meta.sheets.length}\n\n`);
|
|
84
|
-
const sheetRows = meta.sheets.map((s) => {
|
|
85
|
-
const previewCols = (s.columns || []).slice(0, 5).join(", ") + (s.columns && s.columns.length > 5 ? ", ..." : "");
|
|
86
|
-
return [
|
|
87
|
-
s.name,
|
|
88
|
-
formatNumber(s.rowCount),
|
|
89
|
-
s.columnCount !== undefined ? String(s.columnCount) : "-",
|
|
90
|
-
previewCols,
|
|
91
|
-
];
|
|
92
|
-
});
|
|
93
|
-
|
|
94
|
-
process.stdout.write(
|
|
95
|
-
formatTable(
|
|
96
|
-
["SHEET", "ROWS", "COLUMNS", "PREVIEW COLUMNS"],
|
|
97
|
-
sheetRows,
|
|
98
|
-
["left", "right", "right", "left"]
|
|
99
|
-
) + "\n\nTip: Run with --sheet <name> to inspect a specific sheet in full detail.\n"
|
|
100
|
-
);
|
|
101
|
-
}
|
|
102
|
-
logMemoryDebug();
|
|
103
|
-
return;
|
|
104
|
-
}
|
|
105
|
-
|
|
106
|
-
// General inspection across stream
|
|
107
|
-
const schemaAgg = new SchemaInferenceAggregator();
|
|
108
|
-
const statsAgg = new DatasetStatsAggregator();
|
|
109
|
-
|
|
110
|
-
const pipeline = createPipeline(reader);
|
|
111
|
-
pipeline.onProgress((info) => progress.update(info));
|
|
112
|
-
|
|
113
|
-
for await (const row of pipeline.rows()) {
|
|
114
|
-
schemaAgg.add(row);
|
|
115
|
-
statsAgg.add(row);
|
|
116
|
-
}
|
|
117
|
-
|
|
118
|
-
progress.done();
|
|
119
|
-
|
|
120
|
-
const schemaRes = schemaAgg.result();
|
|
121
|
-
const statsRes = statsAgg.result();
|
|
122
|
-
|
|
123
|
-
const totalRows = schemaRes.totalRowsScanned;
|
|
124
|
-
const columnCount = schemaRes.columns.length;
|
|
125
|
-
|
|
126
|
-
const columnDetails = schemaRes.columns.map((col) => {
|
|
127
|
-
const nullPct =
|
|
128
|
-
col.sampleCount > 0 ? (col.nullCount / col.sampleCount) * 100 : 0;
|
|
129
|
-
const colStats = statsRes.columns[col.name];
|
|
130
|
-
const distinctCount =
|
|
131
|
-
colStats?.numeric?.approxDistinct ?? colStats?.string?.approxDistinct ?? 0;
|
|
132
|
-
const uniquePct =
|
|
133
|
-
totalRows > 0 ? Math.min(100, (distinctCount / totalRows) * 100) : 0;
|
|
134
|
-
|
|
135
|
-
return {
|
|
136
|
-
name: col.name,
|
|
137
|
-
type: col.type,
|
|
138
|
-
nullPct,
|
|
139
|
-
uniquePct,
|
|
140
|
-
semantic: col.semantic,
|
|
141
|
-
};
|
|
142
|
-
});
|
|
143
|
-
|
|
144
|
-
if (options.json) {
|
|
145
|
-
const resultJson = {
|
|
146
|
-
file: inputPath === "-" ? "stdin" : inputPath,
|
|
147
|
-
format: format.toUpperCase(),
|
|
148
|
-
sheet: options.sheet,
|
|
149
|
-
sizeBytes: fileSize,
|
|
150
|
-
sizeFormatted: fileSize !== undefined ? formatBytes(fileSize) : undefined,
|
|
151
|
-
rows: totalRows,
|
|
152
|
-
columnsCount: columnCount,
|
|
153
|
-
columns: columnDetails.map((c) => ({
|
|
154
|
-
name: c.name,
|
|
155
|
-
type: c.type,
|
|
156
|
-
nullPercentage: Math.round(c.nullPct * 10) / 10,
|
|
157
|
-
approxUniquePercentage: Math.round(c.uniquePct * 10) / 10,
|
|
158
|
-
semantic: c.semantic,
|
|
159
|
-
})),
|
|
160
|
-
};
|
|
161
|
-
process.stdout.write(JSON.stringify(resultJson, null, 2) + "\n");
|
|
162
|
-
} else {
|
|
163
|
-
process.stdout.write(`File: ${inputPath === "-" ? "stdin" : inputPath}\n`);
|
|
164
|
-
process.stdout.write(`Format: ${format.toUpperCase()}`);
|
|
165
|
-
if (options.sheet) {
|
|
166
|
-
process.stdout.write(` (Sheet: ${options.sheet})`);
|
|
167
|
-
}
|
|
168
|
-
process.stdout.write("\n");
|
|
169
|
-
|
|
170
|
-
if (fileSize !== undefined) {
|
|
171
|
-
process.stdout.write(`Size: ${formatBytes(fileSize)}\n`);
|
|
172
|
-
}
|
|
173
|
-
process.stdout.write(`Rows: ${formatNumber(totalRows)}\n`);
|
|
174
|
-
process.stdout.write(`Columns: ${columnCount}\n\n`);
|
|
175
|
-
|
|
176
|
-
const tableRows = columnDetails.map((c) => [
|
|
177
|
-
c.name,
|
|
178
|
-
c.type,
|
|
179
|
-
`${formatDecimal(c.nullPct, 1)}%`,
|
|
180
|
-
`${formatDecimal(c.uniquePct, 1)}%`,
|
|
181
|
-
]);
|
|
182
|
-
|
|
183
|
-
process.stdout.write(
|
|
184
|
-
formatTable(
|
|
185
|
-
["COLUMN", "TYPE", "NULL", "UNIQUE*"],
|
|
186
|
-
tableRows,
|
|
187
|
-
["left", "left", "right", "right"]
|
|
188
|
-
) + "\n\n* approximate\n"
|
|
189
|
-
);
|
|
190
|
-
}
|
|
191
|
-
|
|
192
|
-
logMemoryDebug();
|
|
193
|
-
}
|
package/src/cli/commands/map.ts
DELETED
|
@@ -1,66 +0,0 @@
|
|
|
1
|
-
import { InvalidArgumentError } from "../../core/errors.js";
|
|
2
|
-
import { createPipeline } from "../../core/pipeline.js";
|
|
3
|
-
import { createReader, inferFormatFromPath as inferReaderFormat } from "../../readers/index.js";
|
|
4
|
-
import { createWriter } from "../../writers/index.js";
|
|
5
|
-
import { mapRows, parseMapSpecs } from "../../transforms/map.js";
|
|
6
|
-
import { openReadableStream } from "../../utils/compression.js";
|
|
7
|
-
import { logMemoryDebug } from "../../utils/formatting.js";
|
|
8
|
-
import { ProgressReporter } from "../../utils/progress.js";
|
|
9
|
-
|
|
10
|
-
export interface MapCommandOptions {
|
|
11
|
-
from?: string;
|
|
12
|
-
to?: string;
|
|
13
|
-
sheet?: string;
|
|
14
|
-
delimiter?: string;
|
|
15
|
-
batchSize?: string | number;
|
|
16
|
-
quiet?: boolean;
|
|
17
|
-
noProgress?: boolean;
|
|
18
|
-
}
|
|
19
|
-
|
|
20
|
-
export async function mapCommand(
|
|
21
|
-
inputPath = "-",
|
|
22
|
-
specs: string[],
|
|
23
|
-
options: MapCommandOptions = {}
|
|
24
|
-
): Promise<void> {
|
|
25
|
-
if (!specs || specs.length === 0) {
|
|
26
|
-
throw new InvalidArgumentError(
|
|
27
|
-
"At least one map specification is required (e.g. rowpipe map users.csv 'full_name=concat(first, \" \", last)')"
|
|
28
|
-
);
|
|
29
|
-
}
|
|
30
|
-
|
|
31
|
-
const effectiveBatchSize = Number(options.batchSize) || 1000;
|
|
32
|
-
const progress = new ProgressReporter(options);
|
|
33
|
-
const parsedSpecs = parseMapSpecs(specs);
|
|
34
|
-
|
|
35
|
-
let fromFormat = options.from?.toLowerCase();
|
|
36
|
-
if (!fromFormat && inputPath !== "-") {
|
|
37
|
-
fromFormat = inferReaderFormat(inputPath) ?? undefined;
|
|
38
|
-
}
|
|
39
|
-
if (!fromFormat) {
|
|
40
|
-
fromFormat = "csv";
|
|
41
|
-
}
|
|
42
|
-
|
|
43
|
-
const toFormat = options.to?.toLowerCase() || (fromFormat === "xlsx" ? "csv" : fromFormat);
|
|
44
|
-
|
|
45
|
-
const inputStream = openReadableStream(inputPath);
|
|
46
|
-
const reader = createReader(inputStream, {
|
|
47
|
-
format: fromFormat,
|
|
48
|
-
sheet: options.sheet,
|
|
49
|
-
delimiter: options.delimiter,
|
|
50
|
-
batchSize: effectiveBatchSize,
|
|
51
|
-
filePath: inputPath,
|
|
52
|
-
});
|
|
53
|
-
|
|
54
|
-
const writer = createWriter(process.stdout, {
|
|
55
|
-
format: toFormat,
|
|
56
|
-
delimiter: options.delimiter,
|
|
57
|
-
});
|
|
58
|
-
|
|
59
|
-
const pipeline = createPipeline(reader, { batchSize: effectiveBatchSize });
|
|
60
|
-
pipeline.pipe(mapRows(parsedSpecs));
|
|
61
|
-
pipeline.onProgress((info) => progress.update(info));
|
|
62
|
-
|
|
63
|
-
await pipeline.to(writer);
|
|
64
|
-
progress.done();
|
|
65
|
-
logMemoryDebug();
|
|
66
|
-
}
|
|
@@ -1,74 +0,0 @@
|
|
|
1
|
-
import { InvalidArgumentError } from "../../core/errors.js";
|
|
2
|
-
import { createPipeline } from "../../core/pipeline.js";
|
|
3
|
-
import { createReader, inferFormatFromPath as inferReaderFormat } from "../../readers/index.js";
|
|
4
|
-
import { createWriter } from "../../writers/index.js";
|
|
5
|
-
import { parseReduceSpecs, reduceRows } from "../../analytics/reduce.js";
|
|
6
|
-
import { openReadableStream } from "../../utils/compression.js";
|
|
7
|
-
import { logMemoryDebug } from "../../utils/formatting.js";
|
|
8
|
-
import { ProgressReporter } from "../../utils/progress.js";
|
|
9
|
-
|
|
10
|
-
export interface ReduceCommandOptions {
|
|
11
|
-
by?: string;
|
|
12
|
-
from?: string;
|
|
13
|
-
to?: string;
|
|
14
|
-
sheet?: string;
|
|
15
|
-
delimiter?: string;
|
|
16
|
-
batchSize?: string | number;
|
|
17
|
-
quiet?: boolean;
|
|
18
|
-
noProgress?: boolean;
|
|
19
|
-
}
|
|
20
|
-
|
|
21
|
-
export async function reduceCommand(
|
|
22
|
-
inputPath = "-",
|
|
23
|
-
specs: string[],
|
|
24
|
-
options: ReduceCommandOptions = {}
|
|
25
|
-
): Promise<void> {
|
|
26
|
-
if (!specs || specs.length === 0) {
|
|
27
|
-
throw new InvalidArgumentError(
|
|
28
|
-
"At least one aggregation specification is required (e.g. rowpipe reduce sales.csv 'total=sum(revenue)' --by country)"
|
|
29
|
-
);
|
|
30
|
-
}
|
|
31
|
-
|
|
32
|
-
const effectiveBatchSize = Number(options.batchSize) || 1000;
|
|
33
|
-
const progress = new ProgressReporter(options);
|
|
34
|
-
const parsedSpecs = parseReduceSpecs(specs);
|
|
35
|
-
|
|
36
|
-
const byCols = options.by
|
|
37
|
-
? options.by
|
|
38
|
-
.split(",")
|
|
39
|
-
.map((c) => c.trim())
|
|
40
|
-
.filter(Boolean)
|
|
41
|
-
: undefined;
|
|
42
|
-
|
|
43
|
-
let fromFormat = options.from?.toLowerCase();
|
|
44
|
-
if (!fromFormat && inputPath !== "-") {
|
|
45
|
-
fromFormat = inferReaderFormat(inputPath) ?? undefined;
|
|
46
|
-
}
|
|
47
|
-
if (!fromFormat) {
|
|
48
|
-
fromFormat = "csv";
|
|
49
|
-
}
|
|
50
|
-
|
|
51
|
-
const toFormat = options.to?.toLowerCase() || (fromFormat === "xlsx" ? "csv" : fromFormat);
|
|
52
|
-
|
|
53
|
-
const inputStream = openReadableStream(inputPath);
|
|
54
|
-
const reader = createReader(inputStream, {
|
|
55
|
-
format: fromFormat,
|
|
56
|
-
sheet: options.sheet,
|
|
57
|
-
delimiter: options.delimiter,
|
|
58
|
-
batchSize: effectiveBatchSize,
|
|
59
|
-
filePath: inputPath,
|
|
60
|
-
});
|
|
61
|
-
|
|
62
|
-
const writer = createWriter(process.stdout, {
|
|
63
|
-
format: toFormat,
|
|
64
|
-
delimiter: options.delimiter,
|
|
65
|
-
});
|
|
66
|
-
|
|
67
|
-
const pipeline = createPipeline(reader, { batchSize: effectiveBatchSize });
|
|
68
|
-
pipeline.pipe(reduceRows({ by: byCols, aggregations: parsedSpecs }));
|
|
69
|
-
pipeline.onProgress((info) => progress.update(info));
|
|
70
|
-
|
|
71
|
-
await pipeline.to(writer);
|
|
72
|
-
progress.done();
|
|
73
|
-
logMemoryDebug();
|
|
74
|
-
}
|
|
@@ -1,59 +0,0 @@
|
|
|
1
|
-
import { createPipeline } from "../../core/pipeline.js";
|
|
2
|
-
import { createReader, inferFormatFromPath as inferReaderFormat } from "../../readers/index.js";
|
|
3
|
-
import { createWriter } from "../../writers/index.js";
|
|
4
|
-
import { parseRenameSpecs, renameColumns } from "../../transforms/rename.js";
|
|
5
|
-
import { openReadableStream } from "../../utils/compression.js";
|
|
6
|
-
import { logMemoryDebug } from "../../utils/formatting.js";
|
|
7
|
-
import { ProgressReporter } from "../../utils/progress.js";
|
|
8
|
-
|
|
9
|
-
export interface RenameCommandOptions {
|
|
10
|
-
from?: string;
|
|
11
|
-
to?: string;
|
|
12
|
-
sheet?: string;
|
|
13
|
-
delimiter?: string;
|
|
14
|
-
batchSize?: string | number;
|
|
15
|
-
quiet?: boolean;
|
|
16
|
-
noProgress?: boolean;
|
|
17
|
-
}
|
|
18
|
-
|
|
19
|
-
export async function renameCommand(
|
|
20
|
-
inputPath = "-",
|
|
21
|
-
specs: string[],
|
|
22
|
-
options: RenameCommandOptions = {}
|
|
23
|
-
): Promise<void> {
|
|
24
|
-
const effectiveBatchSize = Number(options.batchSize) || 1000;
|
|
25
|
-
const progress = new ProgressReporter(options);
|
|
26
|
-
|
|
27
|
-
let fromFormat = options.from?.toLowerCase();
|
|
28
|
-
if (!fromFormat && inputPath !== "-") {
|
|
29
|
-
fromFormat = inferReaderFormat(inputPath) ?? undefined;
|
|
30
|
-
}
|
|
31
|
-
if (!fromFormat) {
|
|
32
|
-
fromFormat = "csv";
|
|
33
|
-
}
|
|
34
|
-
|
|
35
|
-
const toFormat = options.to?.toLowerCase() || (fromFormat === "xlsx" ? "csv" : fromFormat);
|
|
36
|
-
const mapping = parseRenameSpecs(specs);
|
|
37
|
-
|
|
38
|
-
const inputStream = openReadableStream(inputPath);
|
|
39
|
-
const reader = createReader(inputStream, {
|
|
40
|
-
format: fromFormat,
|
|
41
|
-
sheet: options.sheet,
|
|
42
|
-
delimiter: options.delimiter,
|
|
43
|
-
batchSize: effectiveBatchSize,
|
|
44
|
-
filePath: inputPath,
|
|
45
|
-
});
|
|
46
|
-
|
|
47
|
-
const writer = createWriter(process.stdout, {
|
|
48
|
-
format: toFormat,
|
|
49
|
-
delimiter: options.delimiter,
|
|
50
|
-
});
|
|
51
|
-
|
|
52
|
-
const pipeline = createPipeline(reader, { batchSize: effectiveBatchSize });
|
|
53
|
-
pipeline.pipe(renameColumns(mapping));
|
|
54
|
-
pipeline.onProgress((info) => progress.update(info));
|
|
55
|
-
|
|
56
|
-
await pipeline.to(writer);
|
|
57
|
-
progress.done();
|
|
58
|
-
logMemoryDebug();
|
|
59
|
-
}
|
|
@@ -1,61 +0,0 @@
|
|
|
1
|
-
import { createPipeline } from "../../core/pipeline.js";
|
|
2
|
-
import { createReader, inferFormatFromPath as inferReaderFormat } from "../../readers/index.js";
|
|
3
|
-
import { createWriter } from "../../writers/index.js";
|
|
4
|
-
import { sampleRows } from "../../transforms/sample.js";
|
|
5
|
-
import { openReadableStream } from "../../utils/compression.js";
|
|
6
|
-
import { logMemoryDebug } from "../../utils/formatting.js";
|
|
7
|
-
import { ProgressReporter } from "../../utils/progress.js";
|
|
8
|
-
|
|
9
|
-
export interface SampleCommandOptions {
|
|
10
|
-
rows?: string | number;
|
|
11
|
-
seed?: string | number;
|
|
12
|
-
from?: string;
|
|
13
|
-
to?: string;
|
|
14
|
-
sheet?: string;
|
|
15
|
-
delimiter?: string;
|
|
16
|
-
batchSize?: string | number;
|
|
17
|
-
quiet?: boolean;
|
|
18
|
-
noProgress?: boolean;
|
|
19
|
-
}
|
|
20
|
-
|
|
21
|
-
export async function sampleCommand(
|
|
22
|
-
inputPath = "-",
|
|
23
|
-
options: SampleCommandOptions = {}
|
|
24
|
-
): Promise<void> {
|
|
25
|
-
const sampleCount = options.rows !== undefined ? Number(options.rows) : 1000;
|
|
26
|
-
const seed = options.seed !== undefined ? Number(options.seed) : undefined;
|
|
27
|
-
const effectiveBatchSize = Number(options.batchSize) || 1000;
|
|
28
|
-
const progress = new ProgressReporter(options);
|
|
29
|
-
|
|
30
|
-
let fromFormat = options.from?.toLowerCase();
|
|
31
|
-
if (!fromFormat && inputPath !== "-") {
|
|
32
|
-
fromFormat = inferReaderFormat(inputPath) ?? undefined;
|
|
33
|
-
}
|
|
34
|
-
if (!fromFormat) {
|
|
35
|
-
fromFormat = "csv";
|
|
36
|
-
}
|
|
37
|
-
|
|
38
|
-
const toFormat = options.to?.toLowerCase() || (fromFormat === "xlsx" ? "csv" : fromFormat);
|
|
39
|
-
|
|
40
|
-
const inputStream = openReadableStream(inputPath);
|
|
41
|
-
const reader = createReader(inputStream, {
|
|
42
|
-
format: fromFormat,
|
|
43
|
-
sheet: options.sheet,
|
|
44
|
-
delimiter: options.delimiter,
|
|
45
|
-
batchSize: effectiveBatchSize,
|
|
46
|
-
filePath: inputPath,
|
|
47
|
-
});
|
|
48
|
-
|
|
49
|
-
const writer = createWriter(process.stdout, {
|
|
50
|
-
format: toFormat,
|
|
51
|
-
delimiter: options.delimiter,
|
|
52
|
-
});
|
|
53
|
-
|
|
54
|
-
const pipeline = createPipeline(reader, { batchSize: effectiveBatchSize });
|
|
55
|
-
pipeline.pipe(sampleRows({ rows: sampleCount, seed }));
|
|
56
|
-
pipeline.onProgress((info) => progress.update(info));
|
|
57
|
-
|
|
58
|
-
await pipeline.to(writer);
|
|
59
|
-
progress.done();
|
|
60
|
-
logMemoryDebug();
|
|
61
|
-
}
|
|
@@ -1,86 +0,0 @@
|
|
|
1
|
-
import { SchemaInferenceAggregator } from "../../analytics/schema-inference.js";
|
|
2
|
-
import { createPipeline } from "../../core/pipeline.js";
|
|
3
|
-
import { createReader, inferFormatFromPath } from "../../readers/index.js";
|
|
4
|
-
import { openReadableStream } from "../../utils/compression.js";
|
|
5
|
-
import { formatTable, logMemoryDebug } from "../../utils/formatting.js";
|
|
6
|
-
import { ProgressReporter } from "../../utils/progress.js";
|
|
7
|
-
|
|
8
|
-
export interface SchemaCommandOptions {
|
|
9
|
-
from?: string;
|
|
10
|
-
sheet?: string;
|
|
11
|
-
path?: string;
|
|
12
|
-
delimiter?: string;
|
|
13
|
-
sample?: string | number;
|
|
14
|
-
full?: boolean;
|
|
15
|
-
json?: boolean;
|
|
16
|
-
quiet?: boolean;
|
|
17
|
-
noProgress?: boolean;
|
|
18
|
-
}
|
|
19
|
-
|
|
20
|
-
export async function schemaCommand(
|
|
21
|
-
inputPath = "-",
|
|
22
|
-
options: SchemaCommandOptions = {}
|
|
23
|
-
): Promise<void> {
|
|
24
|
-
const progress = new ProgressReporter(options);
|
|
25
|
-
|
|
26
|
-
let fromFormat = options.from?.toLowerCase();
|
|
27
|
-
if (!fromFormat && inputPath !== "-") {
|
|
28
|
-
fromFormat = inferFormatFromPath(inputPath) ?? undefined;
|
|
29
|
-
}
|
|
30
|
-
if (!fromFormat) {
|
|
31
|
-
fromFormat = "csv";
|
|
32
|
-
}
|
|
33
|
-
|
|
34
|
-
const sampleSize = options.full
|
|
35
|
-
? Number.POSITIVE_INFINITY
|
|
36
|
-
: options.sample !== undefined
|
|
37
|
-
? Number(options.sample)
|
|
38
|
-
: 10000;
|
|
39
|
-
|
|
40
|
-
const inputStream = openReadableStream(inputPath);
|
|
41
|
-
const reader = createReader(inputStream, {
|
|
42
|
-
format: fromFormat,
|
|
43
|
-
sheet: options.sheet,
|
|
44
|
-
path: options.path,
|
|
45
|
-
delimiter: options.delimiter,
|
|
46
|
-
filePath: inputPath,
|
|
47
|
-
});
|
|
48
|
-
|
|
49
|
-
const schemaAgg = new SchemaInferenceAggregator({ sample: sampleSize });
|
|
50
|
-
const pipeline = createPipeline(reader);
|
|
51
|
-
pipeline.onProgress((info) => progress.update(info));
|
|
52
|
-
|
|
53
|
-
for await (const row of pipeline.rows()) {
|
|
54
|
-
schemaAgg.add(row);
|
|
55
|
-
}
|
|
56
|
-
|
|
57
|
-
progress.done();
|
|
58
|
-
const res = schemaAgg.result();
|
|
59
|
-
|
|
60
|
-
if (options.json) {
|
|
61
|
-
process.stdout.write(JSON.stringify(res, null, 2) + "\n");
|
|
62
|
-
} else {
|
|
63
|
-
const tableRows = res.columns.map((col) => {
|
|
64
|
-
let typeDisplay = col.type as string;
|
|
65
|
-
if (col.semantic) {
|
|
66
|
-
typeDisplay += ` (${col.semantic})`;
|
|
67
|
-
}
|
|
68
|
-
return [
|
|
69
|
-
col.name,
|
|
70
|
-
typeDisplay,
|
|
71
|
-
col.nullable ? "true" : "false",
|
|
72
|
-
`${col.confidence}%`,
|
|
73
|
-
];
|
|
74
|
-
});
|
|
75
|
-
|
|
76
|
-
process.stdout.write(
|
|
77
|
-
formatTable(
|
|
78
|
-
["COLUMN", "TYPE", "NULLABLE", "CONFIDENCE"],
|
|
79
|
-
tableRows,
|
|
80
|
-
["left", "left", "left", "right"]
|
|
81
|
-
) + "\n"
|
|
82
|
-
);
|
|
83
|
-
}
|
|
84
|
-
|
|
85
|
-
logMemoryDebug();
|
|
86
|
-
}
|
|
@@ -1,59 +0,0 @@
|
|
|
1
|
-
import { createPipeline } from "../../core/pipeline.js";
|
|
2
|
-
import { createReader, inferFormatFromPath as inferReaderFormat } from "../../readers/index.js";
|
|
3
|
-
import { createWriter } from "../../writers/index.js";
|
|
4
|
-
import { selectColumns } from "../../transforms/select.js";
|
|
5
|
-
import { openReadableStream } from "../../utils/compression.js";
|
|
6
|
-
import { logMemoryDebug } from "../../utils/formatting.js";
|
|
7
|
-
import { ProgressReporter } from "../../utils/progress.js";
|
|
8
|
-
|
|
9
|
-
export interface SelectCommandOptions {
|
|
10
|
-
from?: string;
|
|
11
|
-
to?: string;
|
|
12
|
-
sheet?: string;
|
|
13
|
-
delimiter?: string;
|
|
14
|
-
batchSize?: string | number;
|
|
15
|
-
quiet?: boolean;
|
|
16
|
-
noProgress?: boolean;
|
|
17
|
-
}
|
|
18
|
-
|
|
19
|
-
export async function selectCommand(
|
|
20
|
-
inputPath = "-",
|
|
21
|
-
columnsArg: string,
|
|
22
|
-
options: SelectCommandOptions = {}
|
|
23
|
-
): Promise<void> {
|
|
24
|
-
const effectiveBatchSize = Number(options.batchSize) || 1000;
|
|
25
|
-
const progress = new ProgressReporter(options);
|
|
26
|
-
|
|
27
|
-
let fromFormat = options.from?.toLowerCase();
|
|
28
|
-
if (!fromFormat && inputPath !== "-") {
|
|
29
|
-
fromFormat = inferReaderFormat(inputPath) ?? undefined;
|
|
30
|
-
}
|
|
31
|
-
if (!fromFormat) {
|
|
32
|
-
fromFormat = "csv";
|
|
33
|
-
}
|
|
34
|
-
|
|
35
|
-
const toFormat = options.to?.toLowerCase() || (fromFormat === "xlsx" ? "csv" : fromFormat);
|
|
36
|
-
const columns = columnsArg.split(",").map((c) => c.trim());
|
|
37
|
-
|
|
38
|
-
const inputStream = openReadableStream(inputPath);
|
|
39
|
-
const reader = createReader(inputStream, {
|
|
40
|
-
format: fromFormat,
|
|
41
|
-
sheet: options.sheet,
|
|
42
|
-
delimiter: options.delimiter,
|
|
43
|
-
batchSize: effectiveBatchSize,
|
|
44
|
-
filePath: inputPath,
|
|
45
|
-
});
|
|
46
|
-
|
|
47
|
-
const writer = createWriter(process.stdout, {
|
|
48
|
-
format: toFormat,
|
|
49
|
-
delimiter: options.delimiter,
|
|
50
|
-
});
|
|
51
|
-
|
|
52
|
-
const pipeline = createPipeline(reader, { batchSize: effectiveBatchSize });
|
|
53
|
-
pipeline.pipe(selectColumns(columns));
|
|
54
|
-
pipeline.onProgress((info) => progress.update(info));
|
|
55
|
-
|
|
56
|
-
await pipeline.to(writer);
|
|
57
|
-
progress.done();
|
|
58
|
-
logMemoryDebug();
|
|
59
|
-
}
|