]>
Commit | Line | Data |
---|---|---|
1d09f67e TL |
1 | #! /usr/bin/env node |
2 | ||
3 | // Licensed to the Apache Software Foundation (ASF) under one | |
4 | // or more contributor license agreements. See the NOTICE file | |
5 | // distributed with this work for additional information | |
6 | // regarding copyright ownership. The ASF licenses this file | |
7 | // to you under the Apache License, Version 2.0 (the | |
8 | // "License"); you may not use this file except in compliance | |
9 | // with the License. You may obtain a copy of the License at | |
10 | // | |
11 | // http://www.apache.org/licenses/LICENSE-2.0 | |
12 | // | |
13 | // Unless required by applicable law or agreed to in writing, | |
14 | // software distributed under the License is distributed on an | |
15 | // "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY | |
16 | // KIND, either express or implied. See the License for the | |
17 | // specific language governing permissions and limitations | |
18 | // under the License. | |
19 | ||
20 | // @ts-check | |
21 | ||
22 | const fs = require('fs'); | |
23 | const Path = require('path'); | |
24 | const { parse } = require('json-bignum'); | |
25 | const eos = require('util').promisify(require('stream').finished); | |
26 | const extension = process.env.ARROW_JS_DEBUG === 'src' ? '.ts' : ''; | |
27 | const argv = require(`command-line-args`)(cliOpts(), { partial: true }); | |
28 | const { RecordBatchReader, RecordBatchFileWriter, RecordBatchStreamWriter } = require(`../index${extension}`); | |
29 | ||
30 | const jsonPaths = [...(argv.json || [])]; | |
31 | const arrowPaths = [...(argv.arrow || [])]; | |
32 | ||
33 | (async () => { | |
34 | ||
35 | if (!jsonPaths.length || !arrowPaths.length || (jsonPaths.length !== arrowPaths.length)) { | |
36 | return print_usage(); | |
37 | } | |
38 | ||
39 | await Promise.all(jsonPaths.map(async (path, i) => { | |
40 | ||
41 | const RecordBatchWriter = argv.format !== 'stream' | |
42 | ? RecordBatchFileWriter | |
43 | : RecordBatchStreamWriter; | |
44 | ||
45 | const reader = RecordBatchReader.from(parse( | |
46 | await fs.promises.readFile(Path.resolve(path), 'utf8'))); | |
47 | ||
48 | const jsonToArrow = reader | |
49 | .pipe(RecordBatchWriter.throughNode()) | |
50 | .pipe(fs.createWriteStream(arrowPaths[i])); | |
51 | ||
52 | await eos(jsonToArrow); | |
53 | ||
54 | })); | |
55 | })() | |
56 | .then((x) => +x || 0, (e) => { | |
57 | e && process.stderr.write(`${e}`); | |
58 | return process.exitCode || 1; | |
59 | }).then((code = 0) => process.exit(code)); | |
60 | ||
61 | function cliOpts() { | |
62 | return [ | |
63 | { | |
64 | type: String, | |
65 | name: 'format', alias: 'f', | |
66 | multiple: false, defaultValue: 'file', | |
67 | description: 'The Arrow format to write, either "file" or "stream"' | |
68 | }, | |
69 | { | |
70 | type: String, | |
71 | name: 'arrow', alias: 'a', | |
72 | multiple: true, defaultValue: [], | |
73 | description: 'The Arrow file[s] to write' | |
74 | }, | |
75 | { | |
76 | type: String, | |
77 | name: 'json', alias: 'j', | |
78 | multiple: true, defaultValue: [], | |
79 | description: 'The JSON file[s] to read' | |
80 | } | |
81 | ]; | |
82 | } | |
83 | ||
84 | function print_usage() { | |
85 | console.log(require('command-line-usage')([ | |
86 | { | |
87 | header: 'json-to-arrow', | |
88 | content: 'Script for converting a JSON Arrow file to a binary Arrow file' | |
89 | }, | |
90 | { | |
91 | header: 'Synopsis', | |
92 | content: [ | |
93 | '$ json-to-arrow.js -j in.json -a out.arrow -f stream' | |
94 | ] | |
95 | }, | |
96 | { | |
97 | header: 'Options', | |
98 | optionList: [ | |
99 | ...cliOpts(), | |
100 | { | |
101 | name: 'help', | |
102 | description: 'Print this usage guide.' | |
103 | } | |
104 | ] | |
105 | }, | |
106 | ])); | |
107 | return 1; | |
108 | } |