deno.land / std@0.91.0 / encoding / csv.ts

نووسراو ببینە
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
// Ported from Go:// https://github.com/golang/go/blob/go1.12.5/src/encoding/csv/// Copyright 2011 The Go Authors. All rights reserved. BSD license.// https://github.com/golang/go/blob/master/LICENSE// Copyright 2018-2021 the Deno authors. All rights reserved. MIT license.
import { BufReader } from "../io/bufio.ts";import { TextProtoReader } from "../textproto/mod.ts";import { StringReader } from "../io/readers.ts";import { assert } from "../_util/assert.ts";
export { NEWLINE, stringify, StringifyError } from "./csv_stringify.ts";
export type { Column, ColumnDetails, DataItem, StringifyOptions,} from "./csv_stringify.ts";
const INVALID_RUNE = ["\r", "\n", '"'];
export const ERR_BARE_QUOTE = 'bare " in non-quoted-field';export const ERR_QUOTE = 'extraneous or missing " in quoted-field';export const ERR_INVALID_DELIM = "Invalid Delimiter";export const ERR_FIELD_COUNT = "wrong number of fields";
/** * A ParseError is returned for parsing errors. * Line numbers are 1-indexed and columns are 0-indexed. */export class ParseError extends Error { /** Line where the record starts*/ startLine: number; /** Line where the error occurred */ line: number; /** Column (rune index) where the error occurred */ column: number | null;
constructor( start: number, line: number, column: number | null, message: string, ) { super(); this.startLine = start; this.column = column; this.line = line;
if (message === ERR_FIELD_COUNT) { this.message = `record on line ${line}: ${message}`; } else if (start !== line) { this.message = `record on line ${start}; parse error on line ${line}, column ${column}: ${message}`; } else { this.message = `parse error on line ${line}, column ${column}: ${message}`; } }}
/** * @property separator - Character which separates values. Default: ',' * @property comment - Character to start a comment. Default: '#' * @property trimLeadingSpace - Flag to trim the leading space of the value. * Default: 'false' * @property lazyQuotes - Allow unquoted quote in a quoted field or non double * quoted quotes in quoted field. Default: 'false' * @property fieldsPerRecord - Enabling the check of fields for each row. * If == 0, first row is used as referral for the number of fields. */export interface ReadOptions { separator?: string; comment?: string; trimLeadingSpace?: boolean; lazyQuotes?: boolean; fieldsPerRecord?: number;}
function chkOptions(opt: ReadOptions): void { if (!opt.separator) { opt.separator = ","; } if (!opt.trimLeadingSpace) { opt.trimLeadingSpace = false; } if ( INVALID_RUNE.includes(opt.separator) || (typeof opt.comment === "string" && INVALID_RUNE.includes(opt.comment)) || opt.separator === opt.comment ) { throw new Error(ERR_INVALID_DELIM); }}
async function readRecord( startLine: number, reader: BufReader, opt: ReadOptions = { separator: ",", trimLeadingSpace: false },): Promise<string[] | null> { const tp = new TextProtoReader(reader); let line = await readLine(tp); let lineIndex = startLine + 1;
if (line === null) return null; if (line.length === 0) { return []; } // line starting with comment character is ignored if (opt.comment && line[0] === opt.comment) { return []; }
assert(opt.separator != null);
let fullLine = line; let quoteError: ParseError | null = null; const quote = '"'; const quoteLen = quote.length; const separatorLen = opt.separator.length; let recordBuffer = ""; const fieldIndexes = [] as number[]; parseField: for (;;) { if (opt.trimLeadingSpace) { line = line.trimLeft(); }
if (line.length === 0 || !line.startsWith(quote)) { // Non-quoted string field const i = line.indexOf(opt.separator); let field = line; if (i >= 0) { field = field.substring(0, i); } // Check to make sure a quote does not appear in field. if (!opt.lazyQuotes) { const j = field.indexOf(quote); if (j >= 0) { const col = runeCount( fullLine.slice(0, fullLine.length - line.slice(j).length), ); quoteError = new ParseError( startLine + 1, lineIndex, col, ERR_BARE_QUOTE, ); break parseField; } } recordBuffer += field; fieldIndexes.push(recordBuffer.length); if (i >= 0) { line = line.substring(i + separatorLen); continue parseField; } break parseField; } else { // Quoted string field line = line.substring(quoteLen); for (;;) { const i = line.indexOf(quote); if (i >= 0) { // Hit next quote. recordBuffer += line.substring(0, i); line = line.substring(i + quoteLen); if (line.startsWith(quote)) { // `""` sequence (append quote). recordBuffer += quote; line = line.substring(quoteLen); } else if (line.startsWith(opt.separator)) { // `","` sequence (end of field). line = line.substring(separatorLen); fieldIndexes.push(recordBuffer.length); continue parseField; } else if (0 === line.length) { // `"\n` sequence (end of line). fieldIndexes.push(recordBuffer.length); break parseField; } else if (opt.lazyQuotes) { // `"` sequence (bare quote). recordBuffer += quote; } else { // `"*` sequence (invalid non-escaped quote). const col = runeCount( fullLine.slice(0, fullLine.length - line.length - quoteLen), ); quoteError = new ParseError( startLine + 1, lineIndex, col, ERR_QUOTE, ); break parseField; } } else if (line.length > 0 || !(await isEOF(tp))) { // Hit end of line (copy all data so far). recordBuffer += line; const r = await readLine(tp); lineIndex++; line = r ?? ""; // This is a workaround for making this module behave similarly to the encoding/csv/reader.go. fullLine = line; if (r === null) { // Abrupt end of file (EOF or error). if (!opt.lazyQuotes) { const col = runeCount(fullLine); quoteError = new ParseError( startLine + 1, lineIndex, col, ERR_QUOTE, ); break parseField; } fieldIndexes.push(recordBuffer.length); break parseField; } recordBuffer += "\n"; // preserve line feed (This is because TextProtoReader removes it.) } else { // Abrupt end of file (EOF on error). if (!opt.lazyQuotes) { const col = runeCount(fullLine); quoteError = new ParseError( startLine + 1, lineIndex, col, ERR_QUOTE, ); break parseField; } fieldIndexes.push(recordBuffer.length); break parseField; } } } } if (quoteError) { throw quoteError; } const result = [] as string[]; let preIdx = 0; for (const i of fieldIndexes) { result.push(recordBuffer.slice(preIdx, i)); preIdx = i; } return result;}
async function isEOF(tp: TextProtoReader): Promise<boolean> { return (await tp.r.peek(0)) === null;}
function runeCount(s: string): number { // Array.from considers the surrogate pair. return Array.from(s).length;}
async function readLine(tp: TextProtoReader): Promise<string | null> { let line: string; const r = await tp.readLine(); if (r === null) return null; line = r;
// For backwards compatibility, drop trailing \r before EOF. if ((await isEOF(tp)) && line.length > 0 && line[line.length - 1] === "\r") { line = line.substring(0, line.length - 1); }
// Normalize \r\n to \n on all input lines. if ( line.length >= 2 && line[line.length - 2] === "\r" && line[line.length - 1] === "\n" ) { line = line.substring(0, line.length - 2); line = line + "\n"; }
return line;}
/** * Parse the CSV from the `reader` with the options provided and return `string[][]`. * * @param reader provides the CSV data to parse * @param opt controls the parsing behavior */export async function readMatrix( reader: BufReader, opt: ReadOptions = { separator: ",", trimLeadingSpace: false, lazyQuotes: false, },): Promise<string[][]> { const result: string[][] = []; let _nbFields: number | undefined; let lineResult: string[]; let first = true; let lineIndex = 0; chkOptions(opt);
for (;;) { const r = await readRecord(lineIndex, reader, opt); if (r === null) break; lineResult = r; lineIndex++; // If fieldsPerRecord is 0, Read sets it to // the number of fields in the first record if (first) { first = false; if (opt.fieldsPerRecord !== undefined) { if (opt.fieldsPerRecord === 0) { _nbFields = lineResult.length; } else { _nbFields = opt.fieldsPerRecord; } } }
if (lineResult.length > 0) { if (_nbFields && _nbFields !== lineResult.length) { throw new ParseError(lineIndex, lineIndex, null, ERR_FIELD_COUNT); } result.push(lineResult); } } return result;}
/** * Parse the CSV string/buffer with the options provided. * * ColumnOptions provides the column definition * and the parse function for each entry of the * column. */export interface ColumnOptions { /** * Name of the column to be used as property */ name: string; /** * Parse function for the column. * This is executed on each entry of the header. * This can be combined with the Parse function of the rows. */ parse?: (input: string) => unknown;}
export interface ParseOptions extends ReadOptions { /** * If you provide `skipFirstRow: true` and `columns`, the first line will be skipped. * If you provide `skipFirstRow: true` but not `columns`, the first line will be skipped and used as header definitions. */ skipFirstRow?: boolean;
/** * If you provide `string[]` or `ColumnOptions[]`, those names will be used for header definition. */ columns?: string[] | ColumnOptions[];
/** Parse function for rows. * Example: * const r = await parseFile('a,b,c\ne,f,g\n', { * columns: ["this", "is", "sparta"], * parse: (e: Record<string, unknown>) => { * return { super: e.this, street: e.is, fighter: e.sparta }; * } * }); * // output * [ * { super: "a", street: "b", fighter: "c" }, * { super: "e", street: "f", fighter: "g" } * ] */ parse?: (input: unknown) => unknown;}
/** * Csv parse helper to manipulate data. * Provides an auto/custom mapper for columns and parse function * for columns and rows. * @param input Input to parse. Can be a string or BufReader. * @param opt options of the parser. * @returns If you don't provide `opt.skipFirstRow`, `opt.parse`, and `opt.columns`, it returns `string[][]`. * If you provide `opt.skipFirstRow` or `opt.columns` but not `opt.parse`, it returns `object[]`. * If you provide `opt.parse`, it returns an array where each element is the value returned from `opt.parse`. */export async function parse( input: string | BufReader, opt: ParseOptions = { skipFirstRow: false, },): Promise<unknown[]> { let r: string[][]; if (input instanceof BufReader) { r = await readMatrix(input, opt); } else { r = await readMatrix(new BufReader(new StringReader(input)), opt); } if (opt.skipFirstRow || opt.columns) { let headers: ColumnOptions[] = []; let i = 0;
if (opt.skipFirstRow) { const head = r.shift(); assert(head != null); headers = head.map( (e): ColumnOptions => { return { name: e, }; }, ); i++; }
if (opt.columns) { if (typeof opt.columns[0] !== "string") { headers = opt.columns as ColumnOptions[]; } else { const h = opt.columns as string[]; headers = h.map( (e): ColumnOptions => { return { name: e, }; }, ); } } return r.map((e): unknown => { if (e.length !== headers.length) { throw `Error number of fields line:${i}`; } i++; const out: Record<string, unknown> = {}; for (let j = 0; j < e.length; j++) { const h = headers[j]; if (h.parse) { out[h.name] = h.parse(e[j]); } else { out[h.name] = e[j]; } } if (opt.parse) { return opt.parse(out); } return out; }); } if (opt.parse) { return r.map((e: string[]): unknown => { assert(opt.parse, "opt.parse must be set"); return opt.parse(e); }); } return r;}
std

Version Info

Tagged at
3 years ago

External Dependencies

No external dependencies 🎉