@fto-consult/expo-ui 8.72.0 → 8.73.0
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/bin/create-app/dependencies.js +3 -3
- package/package.json +4 -4
- package/src/components/BottomSheet/Sheet.js +1 -1
- package/src/components/Datagrid/Accordion/index.js +1 -1
- package/src/components/Dialog/Dialog.js +5 -2
- package/src/components/Dropdown/index.js +35 -23
- package/src/components/Form/Fields/SelectField.js +1 -1
- package/src/components/Form/Fields/SelectTableData/Component.js +23 -6
- package/src/components/Form/utils/FormsManager.js +11 -5
- package/src/components/List/hooks.js +2 -2
- package/src/components/Menu/Menu.js +5 -3
- package/src/layouts/Screen/TableData.js +1 -2
- package/src/media/Assets/utils.js +9 -2
- package/src/screens/Help/openLibraries.js +81 -124
- package/src/table-data/importer/parser.js +1824 -0
- package/src/table-data/importer/run.js +0 -1
@@ -0,0 +1,1824 @@
|
|
1
|
+
/* @license
|
2
|
+
Papa Parse
|
3
|
+
v5.4.1
|
4
|
+
https://github.com/mholt/PapaParse
|
5
|
+
@see : https://github.com/mholt/PapaParse/tree/master
|
6
|
+
License: MIT
|
7
|
+
*/
|
8
|
+
const global = (function() {
|
9
|
+
// alternative method, similar to `Function('return this')()`
|
10
|
+
// but without using `eval` (which is disabled when
|
11
|
+
// using Content Security Policy).
|
12
|
+
if (typeof self !== 'undefined') { return self; }
|
13
|
+
if (typeof window !== 'undefined') { return window; }
|
14
|
+
if (typeof global !== 'undefined') { return global; }
|
15
|
+
// When running tests none of the above have been defined
|
16
|
+
return {};
|
17
|
+
})();
|
18
|
+
|
19
|
+
function getWorkerBlob() {
|
20
|
+
var URL = global.URL || global.webkitURL || null;
|
21
|
+
var code = moduleFactory.toString();
|
22
|
+
return Papa.BLOB_URL || (Papa.BLOB_URL = URL.createObjectURL(new Blob(["var global = (function() { if (typeof self !== 'undefined') { return self; } if (typeof window !== 'undefined') { return window; } if (typeof global !== 'undefined') { return global; } return {}; })(); global.IS_PAPA_WORKER=true; ", '(', code, ')();'], {type: 'text/javascript'})));
|
23
|
+
}
|
24
|
+
|
25
|
+
var IS_WORKER = !global.document && !!global.postMessage,
|
26
|
+
IS_PAPA_WORKER = global.IS_PAPA_WORKER || false;
|
27
|
+
|
28
|
+
var workers = {}, workerIdCounter = 0;
|
29
|
+
|
30
|
+
const Papa = {};
|
31
|
+
|
32
|
+
Papa.parse = CsvToJson;
|
33
|
+
Papa.unparse = JsonToCsv;
|
34
|
+
|
35
|
+
Papa.RECORD_SEP = String.fromCharCode(30);
|
36
|
+
Papa.UNIT_SEP = String.fromCharCode(31);
|
37
|
+
Papa.BYTE_ORDER_MARK = '\ufeff';
|
38
|
+
Papa.BAD_DELIMITERS = ['\r', '\n', '"', Papa.BYTE_ORDER_MARK];
|
39
|
+
Papa.WORKERS_SUPPORTED = !IS_WORKER && !!global.Worker;
|
40
|
+
Papa.NODE_STREAM_INPUT = 1;
|
41
|
+
|
42
|
+
// Configurable chunk sizes for local and remote files, respectively
|
43
|
+
Papa.LocalChunkSize = 1024 * 1024 * 10; // 10 MB
|
44
|
+
Papa.RemoteChunkSize = 1024 * 1024 * 5; // 5 MB
|
45
|
+
Papa.DefaultDelimiter = ','; // Used if not specified and detection fails
|
46
|
+
|
47
|
+
// Exposed for testing and development only
|
48
|
+
Papa.Parser = Parser;
|
49
|
+
Papa.ParserHandle = ParserHandle;
|
50
|
+
Papa.NetworkStreamer = NetworkStreamer;
|
51
|
+
Papa.FileStreamer = FileStreamer;
|
52
|
+
Papa.StringStreamer = StringStreamer;
|
53
|
+
Papa.ReadableStreamStreamer = ReadableStreamStreamer;
|
54
|
+
if (typeof PAPA_BROWSER_CONTEXT === 'undefined') {
|
55
|
+
Papa.DuplexStreamStreamer = DuplexStreamStreamer;
|
56
|
+
}
|
57
|
+
|
58
|
+
if (IS_PAPA_WORKER)
|
59
|
+
{
|
60
|
+
global.onmessage = workerThreadReceivedMessage;
|
61
|
+
}
|
62
|
+
|
63
|
+
function CsvToJson(_input, _config)
|
64
|
+
{
|
65
|
+
_config = _config || {};
|
66
|
+
var dynamicTyping = _config.dynamicTyping || false;
|
67
|
+
if (isFunction(dynamicTyping)) {
|
68
|
+
_config.dynamicTypingFunction = dynamicTyping;
|
69
|
+
// Will be filled on first row call
|
70
|
+
dynamicTyping = {};
|
71
|
+
}
|
72
|
+
_config.dynamicTyping = dynamicTyping;
|
73
|
+
|
74
|
+
_config.transform = isFunction(_config.transform) ? _config.transform : false;
|
75
|
+
|
76
|
+
if (_config.worker && Papa.WORKERS_SUPPORTED)
|
77
|
+
{
|
78
|
+
var w = newWorker();
|
79
|
+
|
80
|
+
w.userStep = _config.step;
|
81
|
+
w.userChunk = _config.chunk;
|
82
|
+
w.userComplete = _config.complete;
|
83
|
+
w.userError = _config.error;
|
84
|
+
|
85
|
+
_config.step = isFunction(_config.step);
|
86
|
+
_config.chunk = isFunction(_config.chunk);
|
87
|
+
_config.complete = isFunction(_config.complete);
|
88
|
+
_config.error = isFunction(_config.error);
|
89
|
+
delete _config.worker; // prevent infinite loop
|
90
|
+
|
91
|
+
w.postMessage({
|
92
|
+
input: _input,
|
93
|
+
config: _config,
|
94
|
+
workerId: w.id
|
95
|
+
});
|
96
|
+
|
97
|
+
return;
|
98
|
+
}
|
99
|
+
|
100
|
+
var streamer = null;
|
101
|
+
if (_input === Papa.NODE_STREAM_INPUT && typeof PAPA_BROWSER_CONTEXT === 'undefined')
|
102
|
+
{
|
103
|
+
// create a node Duplex stream for use
|
104
|
+
// with .pipe
|
105
|
+
streamer = new DuplexStreamStreamer(_config);
|
106
|
+
return streamer.getStream();
|
107
|
+
}
|
108
|
+
else if (typeof _input === 'string')
|
109
|
+
{
|
110
|
+
_input = stripBom(_input);
|
111
|
+
if (_config.download)
|
112
|
+
streamer = new NetworkStreamer(_config);
|
113
|
+
else
|
114
|
+
streamer = new StringStreamer(_config);
|
115
|
+
}
|
116
|
+
else if (_input.readable === true && isFunction(_input.read) && isFunction(_input.on))
|
117
|
+
{
|
118
|
+
streamer = new ReadableStreamStreamer(_config);
|
119
|
+
}
|
120
|
+
else if ((global.File && _input instanceof File) || _input instanceof Object) // ...Safari. (see issue #106)
|
121
|
+
streamer = new FileStreamer(_config);
|
122
|
+
|
123
|
+
return streamer.stream(_input);
|
124
|
+
|
125
|
+
// Strip character from UTF-8 BOM encoded files that cause issue parsing the file
|
126
|
+
function stripBom(string) {
|
127
|
+
if (string.charCodeAt(0) === 0xfeff) {
|
128
|
+
return string.slice(1);
|
129
|
+
}
|
130
|
+
return string;
|
131
|
+
}
|
132
|
+
}
|
133
|
+
|
134
|
+
function JsonToCsv(_input, _config)
|
135
|
+
{
|
136
|
+
// Default configuration
|
137
|
+
|
138
|
+
/** whether to surround every datum with quotes */
|
139
|
+
var _quotes = false;
|
140
|
+
|
141
|
+
/** whether to write headers */
|
142
|
+
var _writeHeader = true;
|
143
|
+
|
144
|
+
/** delimiting character(s) */
|
145
|
+
var _delimiter = ',';
|
146
|
+
|
147
|
+
/** newline character(s) */
|
148
|
+
var _newline = '\r\n';
|
149
|
+
|
150
|
+
/** quote character */
|
151
|
+
var _quoteChar = '"';
|
152
|
+
|
153
|
+
/** escaped quote character, either "" or <config.escapeChar>" */
|
154
|
+
var _escapedQuote = _quoteChar + _quoteChar;
|
155
|
+
|
156
|
+
/** whether to skip empty lines */
|
157
|
+
var _skipEmptyLines = false;
|
158
|
+
|
159
|
+
/** the columns (keys) we expect when we unparse objects */
|
160
|
+
var _columns = null;
|
161
|
+
|
162
|
+
/** whether to prevent outputting cells that can be parsed as formulae by spreadsheet software (Excel and LibreOffice) */
|
163
|
+
var _escapeFormulae = false;
|
164
|
+
|
165
|
+
unpackConfig();
|
166
|
+
|
167
|
+
var quoteCharRegex = new RegExp(escapeRegExp(_quoteChar), 'g');
|
168
|
+
|
169
|
+
if (typeof _input === 'string')
|
170
|
+
_input = JSON.parse(_input);
|
171
|
+
|
172
|
+
if (Array.isArray(_input))
|
173
|
+
{
|
174
|
+
if (!_input.length || Array.isArray(_input[0]))
|
175
|
+
return serialize(null, _input, _skipEmptyLines);
|
176
|
+
else if (typeof _input[0] === 'object')
|
177
|
+
return serialize(_columns || Object.keys(_input[0]), _input, _skipEmptyLines);
|
178
|
+
}
|
179
|
+
else if (typeof _input === 'object')
|
180
|
+
{
|
181
|
+
if (typeof _input.data === 'string')
|
182
|
+
_input.data = JSON.parse(_input.data);
|
183
|
+
|
184
|
+
if (Array.isArray(_input.data))
|
185
|
+
{
|
186
|
+
if (!_input.fields)
|
187
|
+
_input.fields = _input.meta && _input.meta.fields || _columns;
|
188
|
+
|
189
|
+
if (!_input.fields)
|
190
|
+
_input.fields = Array.isArray(_input.data[0])
|
191
|
+
? _input.fields
|
192
|
+
: typeof _input.data[0] === 'object'
|
193
|
+
? Object.keys(_input.data[0])
|
194
|
+
: [];
|
195
|
+
|
196
|
+
if (!(Array.isArray(_input.data[0])) && typeof _input.data[0] !== 'object')
|
197
|
+
_input.data = [_input.data]; // handles input like [1,2,3] or ['asdf']
|
198
|
+
}
|
199
|
+
|
200
|
+
return serialize(_input.fields || [], _input.data || [], _skipEmptyLines);
|
201
|
+
}
|
202
|
+
|
203
|
+
// Default (any valid paths should return before this)
|
204
|
+
throw new Error('Unable to serialize unrecognized input');
|
205
|
+
|
206
|
+
|
207
|
+
function unpackConfig()
|
208
|
+
{
|
209
|
+
if (typeof _config !== 'object')
|
210
|
+
return;
|
211
|
+
|
212
|
+
if (typeof _config.delimiter === 'string'
|
213
|
+
&& !Papa.BAD_DELIMITERS.filter(function(value) { return _config.delimiter.indexOf(value) !== -1; }).length)
|
214
|
+
{
|
215
|
+
_delimiter = _config.delimiter;
|
216
|
+
}
|
217
|
+
|
218
|
+
if (typeof _config.quotes === 'boolean'
|
219
|
+
|| typeof _config.quotes === 'function'
|
220
|
+
|| Array.isArray(_config.quotes))
|
221
|
+
_quotes = _config.quotes;
|
222
|
+
|
223
|
+
if (typeof _config.skipEmptyLines === 'boolean'
|
224
|
+
|| typeof _config.skipEmptyLines === 'string')
|
225
|
+
_skipEmptyLines = _config.skipEmptyLines;
|
226
|
+
|
227
|
+
if (typeof _config.newline === 'string')
|
228
|
+
_newline = _config.newline;
|
229
|
+
|
230
|
+
if (typeof _config.quoteChar === 'string')
|
231
|
+
_quoteChar = _config.quoteChar;
|
232
|
+
|
233
|
+
if (typeof _config.header === 'boolean')
|
234
|
+
_writeHeader = _config.header;
|
235
|
+
|
236
|
+
if (Array.isArray(_config.columns)) {
|
237
|
+
|
238
|
+
if (_config.columns.length === 0) throw new Error('Option columns is empty');
|
239
|
+
|
240
|
+
_columns = _config.columns;
|
241
|
+
}
|
242
|
+
|
243
|
+
if (_config.escapeChar !== undefined) {
|
244
|
+
_escapedQuote = _config.escapeChar + _quoteChar;
|
245
|
+
}
|
246
|
+
|
247
|
+
if (_config.escapeFormulae instanceof RegExp) {
|
248
|
+
_escapeFormulae = _config.escapeFormulae;
|
249
|
+
} else if (typeof _config.escapeFormulae === 'boolean' && _config.escapeFormulae) {
|
250
|
+
_escapeFormulae = /^[=+\-@\t\r].*$/;
|
251
|
+
}
|
252
|
+
}
|
253
|
+
|
254
|
+
/** The double for loop that iterates the data and writes out a CSV string including header row */
|
255
|
+
function serialize(fields, data, skipEmptyLines)
|
256
|
+
{
|
257
|
+
var csv = '';
|
258
|
+
|
259
|
+
if (typeof fields === 'string')
|
260
|
+
fields = JSON.parse(fields);
|
261
|
+
if (typeof data === 'string')
|
262
|
+
data = JSON.parse(data);
|
263
|
+
|
264
|
+
var hasHeader = Array.isArray(fields) && fields.length > 0;
|
265
|
+
var dataKeyedByField = !(Array.isArray(data[0]));
|
266
|
+
|
267
|
+
// If there a header row, write it first
|
268
|
+
if (hasHeader && _writeHeader)
|
269
|
+
{
|
270
|
+
for (var i = 0; i < fields.length; i++)
|
271
|
+
{
|
272
|
+
if (i > 0)
|
273
|
+
csv += _delimiter;
|
274
|
+
csv += safe(fields[i], i);
|
275
|
+
}
|
276
|
+
if (data.length > 0)
|
277
|
+
csv += _newline;
|
278
|
+
}
|
279
|
+
|
280
|
+
// Then write out the data
|
281
|
+
for (var row = 0; row < data.length; row++)
|
282
|
+
{
|
283
|
+
var maxCol = hasHeader ? fields.length : data[row].length;
|
284
|
+
|
285
|
+
var emptyLine = false;
|
286
|
+
var nullLine = hasHeader ? Object.keys(data[row]).length === 0 : data[row].length === 0;
|
287
|
+
if (skipEmptyLines && !hasHeader)
|
288
|
+
{
|
289
|
+
emptyLine = skipEmptyLines === 'greedy' ? data[row].join('').trim() === '' : data[row].length === 1 && data[row][0].length === 0;
|
290
|
+
}
|
291
|
+
if (skipEmptyLines === 'greedy' && hasHeader) {
|
292
|
+
var line = [];
|
293
|
+
for (var c = 0; c < maxCol; c++) {
|
294
|
+
var cx = dataKeyedByField ? fields[c] : c;
|
295
|
+
line.push(data[row][cx]);
|
296
|
+
}
|
297
|
+
emptyLine = line.join('').trim() === '';
|
298
|
+
}
|
299
|
+
if (!emptyLine)
|
300
|
+
{
|
301
|
+
for (var col = 0; col < maxCol; col++)
|
302
|
+
{
|
303
|
+
if (col > 0 && !nullLine)
|
304
|
+
csv += _delimiter;
|
305
|
+
var colIdx = hasHeader && dataKeyedByField ? fields[col] : col;
|
306
|
+
csv += safe(data[row][colIdx], col);
|
307
|
+
}
|
308
|
+
if (row < data.length - 1 && (!skipEmptyLines || (maxCol > 0 && !nullLine)))
|
309
|
+
{
|
310
|
+
csv += _newline;
|
311
|
+
}
|
312
|
+
}
|
313
|
+
}
|
314
|
+
return csv;
|
315
|
+
}
|
316
|
+
|
317
|
+
/** Encloses a value around quotes if needed (makes a value safe for CSV insertion) */
|
318
|
+
function safe(str, col)
|
319
|
+
{
|
320
|
+
if (typeof str === 'undefined' || str === null)
|
321
|
+
return '';
|
322
|
+
|
323
|
+
if (str.constructor === Date)
|
324
|
+
return JSON.stringify(str).slice(1, 25);
|
325
|
+
|
326
|
+
var needsQuotes = false;
|
327
|
+
|
328
|
+
if (_escapeFormulae && typeof str === "string" && _escapeFormulae.test(str)) {
|
329
|
+
str = "'" + str;
|
330
|
+
needsQuotes = true;
|
331
|
+
}
|
332
|
+
|
333
|
+
var escapedQuoteStr = str.toString().replace(quoteCharRegex, _escapedQuote);
|
334
|
+
|
335
|
+
needsQuotes = needsQuotes
|
336
|
+
|| _quotes === true
|
337
|
+
|| (typeof _quotes === 'function' && _quotes(str, col))
|
338
|
+
|| (Array.isArray(_quotes) && _quotes[col])
|
339
|
+
|| hasAny(escapedQuoteStr, Papa.BAD_DELIMITERS)
|
340
|
+
|| escapedQuoteStr.indexOf(_delimiter) > -1
|
341
|
+
|| escapedQuoteStr.charAt(0) === ' '
|
342
|
+
|| escapedQuoteStr.charAt(escapedQuoteStr.length - 1) === ' ';
|
343
|
+
|
344
|
+
return needsQuotes ? _quoteChar + escapedQuoteStr + _quoteChar : escapedQuoteStr;
|
345
|
+
}
|
346
|
+
|
347
|
+
function hasAny(str, substrings)
|
348
|
+
{
|
349
|
+
for (var i = 0; i < substrings.length; i++)
|
350
|
+
if (str.indexOf(substrings[i]) > -1)
|
351
|
+
return true;
|
352
|
+
return false;
|
353
|
+
}
|
354
|
+
}
|
355
|
+
|
356
|
+
|
357
|
+
/** ChunkStreamer is the base prototype for various streamer implementations. */
|
358
|
+
function ChunkStreamer(config)
|
359
|
+
{
|
360
|
+
this._handle = null;
|
361
|
+
this._finished = false;
|
362
|
+
this._completed = false;
|
363
|
+
this._halted = false;
|
364
|
+
this._input = null;
|
365
|
+
this._baseIndex = 0;
|
366
|
+
this._partialLine = '';
|
367
|
+
this._rowCount = 0;
|
368
|
+
this._start = 0;
|
369
|
+
this._nextChunk = null;
|
370
|
+
this.isFirstChunk = true;
|
371
|
+
this._completeResults = {
|
372
|
+
data: [],
|
373
|
+
errors: [],
|
374
|
+
meta: {}
|
375
|
+
};
|
376
|
+
replaceConfig.call(this, config);
|
377
|
+
|
378
|
+
this.parseChunk = function(chunk, isFakeChunk)
|
379
|
+
{
|
380
|
+
// First chunk pre-processing
|
381
|
+
if (this.isFirstChunk && isFunction(this._config.beforeFirstChunk))
|
382
|
+
{
|
383
|
+
var modifiedChunk = this._config.beforeFirstChunk(chunk);
|
384
|
+
if (modifiedChunk !== undefined)
|
385
|
+
chunk = modifiedChunk;
|
386
|
+
}
|
387
|
+
this.isFirstChunk = false;
|
388
|
+
this._halted = false;
|
389
|
+
|
390
|
+
// Rejoin the line we likely just split in two by chunking the file
|
391
|
+
var aggregate = this._partialLine + chunk;
|
392
|
+
this._pendingSkip = parseInt(this._config.skipFirstNLines) || 0;
|
393
|
+
this._skipHeader = 0;
|
394
|
+
if (this._config.header) {
|
395
|
+
this._skipHeader++;
|
396
|
+
}
|
397
|
+
if (this._pendingSkip > 0) {
|
398
|
+
var splitChunk = aggregate.split('\n');
|
399
|
+
var currentChunkLength = splitChunk.length;
|
400
|
+
if (currentChunkLength <= this._pendingSkip) {
|
401
|
+
aggregate = this._partialLine;
|
402
|
+
}
|
403
|
+
else{
|
404
|
+
aggregate = this._partialLine + [...splitChunk.slice(0, this._skipHeader), ...splitChunk.slice(this._skipHeader + this._pendingSkip)].join('\n');
|
405
|
+
}
|
406
|
+
this._pendingSkip -= currentChunkLength;
|
407
|
+
}
|
408
|
+
this._partialLine = '';
|
409
|
+
var results = this._handle.parse(aggregate, this._baseIndex, !this._finished);
|
410
|
+
|
411
|
+
if (this._handle.paused() || this._handle.aborted()) {
|
412
|
+
this._halted = true;
|
413
|
+
return;
|
414
|
+
}
|
415
|
+
|
416
|
+
var lastIndex = results.meta.cursor;
|
417
|
+
|
418
|
+
if (!this._finished)
|
419
|
+
{
|
420
|
+
this._partialLine = aggregate.substring(lastIndex - this._baseIndex);
|
421
|
+
this._baseIndex = lastIndex;
|
422
|
+
}
|
423
|
+
|
424
|
+
if (results && results.data)
|
425
|
+
this._rowCount += results.data.length;
|
426
|
+
|
427
|
+
var finishedIncludingPreview = this._finished || (this._config.preview && this._rowCount >= this._config.preview);
|
428
|
+
|
429
|
+
if (IS_PAPA_WORKER)
|
430
|
+
{
|
431
|
+
global.postMessage({
|
432
|
+
results: results,
|
433
|
+
workerId: Papa.WORKER_ID,
|
434
|
+
finished: finishedIncludingPreview
|
435
|
+
});
|
436
|
+
}
|
437
|
+
else if (isFunction(this._config.chunk) && !isFakeChunk)
|
438
|
+
{
|
439
|
+
this._config.chunk(results, this._handle);
|
440
|
+
if (this._handle.paused() || this._handle.aborted()) {
|
441
|
+
this._halted = true;
|
442
|
+
return;
|
443
|
+
}
|
444
|
+
results = undefined;
|
445
|
+
this._completeResults = undefined;
|
446
|
+
}
|
447
|
+
|
448
|
+
if (!this._config.step && !this._config.chunk) {
|
449
|
+
this._completeResults.data = this._completeResults.data.concat(results.data);
|
450
|
+
this._completeResults.errors = this._completeResults.errors.concat(results.errors);
|
451
|
+
this._completeResults.meta = results.meta;
|
452
|
+
}
|
453
|
+
|
454
|
+
if (!this._completed && finishedIncludingPreview && isFunction(this._config.complete) && (!results || !results.meta.aborted)) {
|
455
|
+
this._config.complete(this._completeResults, this._input);
|
456
|
+
this._completed = true;
|
457
|
+
}
|
458
|
+
|
459
|
+
if (!finishedIncludingPreview && (!results || !results.meta.paused))
|
460
|
+
this._nextChunk();
|
461
|
+
|
462
|
+
return results;
|
463
|
+
};
|
464
|
+
|
465
|
+
this._sendError = function(error)
|
466
|
+
{
|
467
|
+
if (isFunction(this._config.error))
|
468
|
+
this._config.error(error);
|
469
|
+
else if (IS_PAPA_WORKER && this._config.error)
|
470
|
+
{
|
471
|
+
global.postMessage({
|
472
|
+
workerId: Papa.WORKER_ID,
|
473
|
+
error: error,
|
474
|
+
finished: false
|
475
|
+
});
|
476
|
+
}
|
477
|
+
};
|
478
|
+
|
479
|
+
function replaceConfig(config)
|
480
|
+
{
|
481
|
+
// Deep-copy the config so we can edit it
|
482
|
+
var configCopy = copy(config);
|
483
|
+
configCopy.chunkSize = parseInt(configCopy.chunkSize); // parseInt VERY important so we don't concatenate strings!
|
484
|
+
if (!config.step && !config.chunk)
|
485
|
+
configCopy.chunkSize = null; // disable Range header if not streaming; bad values break IIS - see issue #196
|
486
|
+
this._handle = new ParserHandle(configCopy);
|
487
|
+
this._handle.streamer = this;
|
488
|
+
this._config = configCopy; // persist the copy to the caller
|
489
|
+
}
|
490
|
+
}
|
491
|
+
|
492
|
+
|
493
|
+
function NetworkStreamer(config)
|
494
|
+
{
|
495
|
+
config = config || {};
|
496
|
+
if (!config.chunkSize)
|
497
|
+
config.chunkSize = Papa.RemoteChunkSize;
|
498
|
+
ChunkStreamer.call(this, config);
|
499
|
+
|
500
|
+
var xhr;
|
501
|
+
|
502
|
+
if (IS_WORKER)
|
503
|
+
{
|
504
|
+
this._nextChunk = function()
|
505
|
+
{
|
506
|
+
this._readChunk();
|
507
|
+
this._chunkLoaded();
|
508
|
+
};
|
509
|
+
}
|
510
|
+
else
|
511
|
+
{
|
512
|
+
this._nextChunk = function()
|
513
|
+
{
|
514
|
+
this._readChunk();
|
515
|
+
};
|
516
|
+
}
|
517
|
+
|
518
|
+
this.stream = function(url)
|
519
|
+
{
|
520
|
+
this._input = url;
|
521
|
+
this._nextChunk(); // Starts streaming
|
522
|
+
};
|
523
|
+
|
524
|
+
this._readChunk = function()
|
525
|
+
{
|
526
|
+
if (this._finished)
|
527
|
+
{
|
528
|
+
this._chunkLoaded();
|
529
|
+
return;
|
530
|
+
}
|
531
|
+
|
532
|
+
xhr = new XMLHttpRequest();
|
533
|
+
|
534
|
+
if (this._config.withCredentials)
|
535
|
+
{
|
536
|
+
xhr.withCredentials = this._config.withCredentials;
|
537
|
+
}
|
538
|
+
|
539
|
+
if (!IS_WORKER)
|
540
|
+
{
|
541
|
+
xhr.onload = bindFunction(this._chunkLoaded, this);
|
542
|
+
xhr.onerror = bindFunction(this._chunkError, this);
|
543
|
+
}
|
544
|
+
|
545
|
+
xhr.open(this._config.downloadRequestBody ? 'POST' : 'GET', this._input, !IS_WORKER);
|
546
|
+
// Headers can only be set when once the request state is OPENED
|
547
|
+
if (this._config.downloadRequestHeaders)
|
548
|
+
{
|
549
|
+
var headers = this._config.downloadRequestHeaders;
|
550
|
+
|
551
|
+
for (var headerName in headers)
|
552
|
+
{
|
553
|
+
xhr.setRequestHeader(headerName, headers[headerName]);
|
554
|
+
}
|
555
|
+
}
|
556
|
+
|
557
|
+
if (this._config.chunkSize)
|
558
|
+
{
|
559
|
+
var end = this._start + this._config.chunkSize - 1; // minus one because byte range is inclusive
|
560
|
+
xhr.setRequestHeader('Range', 'bytes=' + this._start + '-' + end);
|
561
|
+
}
|
562
|
+
|
563
|
+
try {
|
564
|
+
xhr.send(this._config.downloadRequestBody);
|
565
|
+
}
|
566
|
+
catch (err) {
|
567
|
+
this._chunkError(err.message);
|
568
|
+
}
|
569
|
+
|
570
|
+
if (IS_WORKER && xhr.status === 0)
|
571
|
+
this._chunkError();
|
572
|
+
};
|
573
|
+
|
574
|
+
this._chunkLoaded = function()
|
575
|
+
{
|
576
|
+
if (xhr.readyState !== 4)
|
577
|
+
return;
|
578
|
+
|
579
|
+
if (xhr.status < 200 || xhr.status >= 400)
|
580
|
+
{
|
581
|
+
this._chunkError();
|
582
|
+
return;
|
583
|
+
}
|
584
|
+
|
585
|
+
// Use chunckSize as it may be a diference on reponse lentgh due to characters with more than 1 byte
|
586
|
+
this._start += this._config.chunkSize ? this._config.chunkSize : xhr.responseText.length;
|
587
|
+
this._finished = !this._config.chunkSize || this._start >= getFileSize(xhr);
|
588
|
+
this.parseChunk(xhr.responseText);
|
589
|
+
};
|
590
|
+
|
591
|
+
this._chunkError = function(errorMessage)
|
592
|
+
{
|
593
|
+
var errorText = xhr.statusText || errorMessage;
|
594
|
+
this._sendError(new Error(errorText));
|
595
|
+
};
|
596
|
+
|
597
|
+
function getFileSize(xhr)
|
598
|
+
{
|
599
|
+
var contentRange = xhr.getResponseHeader('Content-Range');
|
600
|
+
if (contentRange === null) { // no content range, then finish!
|
601
|
+
return -1;
|
602
|
+
}
|
603
|
+
return parseInt(contentRange.substring(contentRange.lastIndexOf('/') + 1));
|
604
|
+
}
|
605
|
+
}
|
606
|
+
NetworkStreamer.prototype = Object.create(ChunkStreamer.prototype);
|
607
|
+
NetworkStreamer.prototype.constructor = NetworkStreamer;
|
608
|
+
|
609
|
+
|
610
|
+
function FileStreamer(config)
|
611
|
+
{
|
612
|
+
config = config || {};
|
613
|
+
if (!config.chunkSize)
|
614
|
+
config.chunkSize = Papa.LocalChunkSize;
|
615
|
+
ChunkStreamer.call(this, config);
|
616
|
+
|
617
|
+
var reader, slice;
|
618
|
+
|
619
|
+
// FileReader is better than FileReaderSync (even in worker) - see http://stackoverflow.com/q/24708649/1048862
|
620
|
+
// But Firefox is a pill, too - see issue #76: https://github.com/mholt/PapaParse/issues/76
|
621
|
+
var usingAsyncReader = typeof FileReader !== 'undefined'; // Safari doesn't consider it a function - see issue #105
|
622
|
+
|
623
|
+
this.stream = function(file)
|
624
|
+
{
|
625
|
+
this._input = file;
|
626
|
+
slice = file.slice || file.webkitSlice || file.mozSlice;
|
627
|
+
|
628
|
+
if (usingAsyncReader)
|
629
|
+
{
|
630
|
+
reader = new FileReader(); // Preferred method of reading files, even in workers
|
631
|
+
reader.onload = bindFunction(this._chunkLoaded, this);
|
632
|
+
reader.onerror = bindFunction(this._chunkError, this);
|
633
|
+
}
|
634
|
+
else
|
635
|
+
reader = new FileReaderSync(); // Hack for running in a web worker in Firefox
|
636
|
+
|
637
|
+
this._nextChunk(); // Starts streaming
|
638
|
+
};
|
639
|
+
|
640
|
+
this._nextChunk = function()
|
641
|
+
{
|
642
|
+
if (!this._finished && (!this._config.preview || this._rowCount < this._config.preview))
|
643
|
+
this._readChunk();
|
644
|
+
};
|
645
|
+
|
646
|
+
this._readChunk = function()
|
647
|
+
{
|
648
|
+
var input = this._input;
|
649
|
+
if (this._config.chunkSize)
|
650
|
+
{
|
651
|
+
var end = Math.min(this._start + this._config.chunkSize, this._input.size);
|
652
|
+
input = slice.call(input, this._start, end);
|
653
|
+
}
|
654
|
+
var txt = reader.readAsText(input, this._config.encoding);
|
655
|
+
if (!usingAsyncReader)
|
656
|
+
this._chunkLoaded({ target: { result: txt } }); // mimic the async signature
|
657
|
+
};
|
658
|
+
|
659
|
+
this._chunkLoaded = function(event)
|
660
|
+
{
|
661
|
+
// Very important to increment start each time before handling results
|
662
|
+
this._start += this._config.chunkSize;
|
663
|
+
this._finished = !this._config.chunkSize || this._start >= this._input.size;
|
664
|
+
this.parseChunk(event.target.result);
|
665
|
+
};
|
666
|
+
|
667
|
+
this._chunkError = function()
|
668
|
+
{
|
669
|
+
this._sendError(reader.error);
|
670
|
+
};
|
671
|
+
|
672
|
+
}
|
673
|
+
FileStreamer.prototype = Object.create(ChunkStreamer.prototype);
|
674
|
+
FileStreamer.prototype.constructor = FileStreamer;
|
675
|
+
|
676
|
+
|
677
|
+
function StringStreamer(config)
|
678
|
+
{
|
679
|
+
config = config || {};
|
680
|
+
ChunkStreamer.call(this, config);
|
681
|
+
|
682
|
+
var remaining;
|
683
|
+
this.stream = function(s)
|
684
|
+
{
|
685
|
+
remaining = s;
|
686
|
+
return this._nextChunk();
|
687
|
+
};
|
688
|
+
this._nextChunk = function()
|
689
|
+
{
|
690
|
+
if (this._finished) return;
|
691
|
+
var size = this._config.chunkSize;
|
692
|
+
var chunk;
|
693
|
+
if(size) {
|
694
|
+
chunk = remaining.substring(0, size);
|
695
|
+
remaining = remaining.substring(size);
|
696
|
+
} else {
|
697
|
+
chunk = remaining;
|
698
|
+
remaining = '';
|
699
|
+
}
|
700
|
+
this._finished = !remaining;
|
701
|
+
return this.parseChunk(chunk);
|
702
|
+
};
|
703
|
+
}
|
704
|
+
StringStreamer.prototype = Object.create(StringStreamer.prototype);
|
705
|
+
StringStreamer.prototype.constructor = StringStreamer;
|
706
|
+
|
707
|
+
|
708
|
+
function ReadableStreamStreamer(config)
|
709
|
+
{
|
710
|
+
config = config || {};
|
711
|
+
|
712
|
+
ChunkStreamer.call(this, config);
|
713
|
+
|
714
|
+
var queue = [];
|
715
|
+
var parseOnData = true;
|
716
|
+
var streamHasEnded = false;
|
717
|
+
|
718
|
+
this.pause = function()
|
719
|
+
{
|
720
|
+
ChunkStreamer.prototype.pause.apply(this, arguments);
|
721
|
+
this._input.pause();
|
722
|
+
};
|
723
|
+
|
724
|
+
this.resume = function()
|
725
|
+
{
|
726
|
+
ChunkStreamer.prototype.resume.apply(this, arguments);
|
727
|
+
this._input.resume();
|
728
|
+
};
|
729
|
+
|
730
|
+
this.stream = function(stream)
|
731
|
+
{
|
732
|
+
this._input = stream;
|
733
|
+
|
734
|
+
this._input.on('data', this._streamData);
|
735
|
+
this._input.on('end', this._streamEnd);
|
736
|
+
this._input.on('error', this._streamError);
|
737
|
+
};
|
738
|
+
|
739
|
+
this._checkIsFinished = function()
|
740
|
+
{
|
741
|
+
if (streamHasEnded && queue.length === 1) {
|
742
|
+
this._finished = true;
|
743
|
+
}
|
744
|
+
};
|
745
|
+
|
746
|
+
this._nextChunk = function()
|
747
|
+
{
|
748
|
+
this._checkIsFinished();
|
749
|
+
if (queue.length)
|
750
|
+
{
|
751
|
+
this.parseChunk(queue.shift());
|
752
|
+
}
|
753
|
+
else
|
754
|
+
{
|
755
|
+
parseOnData = true;
|
756
|
+
}
|
757
|
+
};
|
758
|
+
|
759
|
+
this._streamData = bindFunction(function(chunk)
|
760
|
+
{
|
761
|
+
try
|
762
|
+
{
|
763
|
+
queue.push(typeof chunk === 'string' ? chunk : chunk.toString(this._config.encoding));
|
764
|
+
|
765
|
+
if (parseOnData)
|
766
|
+
{
|
767
|
+
parseOnData = false;
|
768
|
+
this._checkIsFinished();
|
769
|
+
this.parseChunk(queue.shift());
|
770
|
+
}
|
771
|
+
}
|
772
|
+
catch (error)
|
773
|
+
{
|
774
|
+
this._streamError(error);
|
775
|
+
}
|
776
|
+
}, this);
|
777
|
+
|
778
|
+
this._streamError = bindFunction(function(error)
|
779
|
+
{
|
780
|
+
this._streamCleanUp();
|
781
|
+
this._sendError(error);
|
782
|
+
}, this);
|
783
|
+
|
784
|
+
this._streamEnd = bindFunction(function()
|
785
|
+
{
|
786
|
+
this._streamCleanUp();
|
787
|
+
streamHasEnded = true;
|
788
|
+
this._streamData('');
|
789
|
+
}, this);
|
790
|
+
|
791
|
+
this._streamCleanUp = bindFunction(function()
|
792
|
+
{
|
793
|
+
this._input.removeListener('data', this._streamData);
|
794
|
+
this._input.removeListener('end', this._streamEnd);
|
795
|
+
this._input.removeListener('error', this._streamError);
|
796
|
+
}, this);
|
797
|
+
}
|
798
|
+
ReadableStreamStreamer.prototype = Object.create(ChunkStreamer.prototype);
|
799
|
+
ReadableStreamStreamer.prototype.constructor = ReadableStreamStreamer;
|
800
|
+
|
801
|
+
|
802
|
+
function DuplexStreamStreamer(_config) {
|
803
|
+
var Duplex = require('stream').Duplex;
|
804
|
+
var config = copy(_config);
|
805
|
+
var parseOnWrite = true;
|
806
|
+
var writeStreamHasFinished = false;
|
807
|
+
var parseCallbackQueue = [];
|
808
|
+
var stream = null;
|
809
|
+
|
810
|
+
this._onCsvData = function(results)
|
811
|
+
{
|
812
|
+
var data = results.data;
|
813
|
+
if (!stream.push(data) && !this._handle.paused()) {
|
814
|
+
// the writeable consumer buffer has filled up
|
815
|
+
// so we need to pause until more items
|
816
|
+
// can be processed
|
817
|
+
this._handle.pause();
|
818
|
+
}
|
819
|
+
};
|
820
|
+
|
821
|
+
this._onCsvComplete = function()
|
822
|
+
{
|
823
|
+
// node will finish the read stream when
|
824
|
+
// null is pushed
|
825
|
+
stream.push(null);
|
826
|
+
};
|
827
|
+
|
828
|
+
config.step = bindFunction(this._onCsvData, this);
|
829
|
+
config.complete = bindFunction(this._onCsvComplete, this);
|
830
|
+
ChunkStreamer.call(this, config);
|
831
|
+
|
832
|
+
this._nextChunk = function()
|
833
|
+
{
|
834
|
+
if (writeStreamHasFinished && parseCallbackQueue.length === 1) {
|
835
|
+
this._finished = true;
|
836
|
+
}
|
837
|
+
if (parseCallbackQueue.length) {
|
838
|
+
parseCallbackQueue.shift()();
|
839
|
+
} else {
|
840
|
+
parseOnWrite = true;
|
841
|
+
}
|
842
|
+
};
|
843
|
+
|
844
|
+
this._addToParseQueue = function(chunk, callback)
|
845
|
+
{
|
846
|
+
// add to queue so that we can indicate
|
847
|
+
// completion via callback
|
848
|
+
// node will automatically pause the incoming stream
|
849
|
+
// when too many items have been added without their
|
850
|
+
// callback being invoked
|
851
|
+
parseCallbackQueue.push(bindFunction(function() {
|
852
|
+
this.parseChunk(typeof chunk === 'string' ? chunk : chunk.toString(config.encoding));
|
853
|
+
if (isFunction(callback)) {
|
854
|
+
return callback();
|
855
|
+
}
|
856
|
+
}, this));
|
857
|
+
if (parseOnWrite) {
|
858
|
+
parseOnWrite = false;
|
859
|
+
this._nextChunk();
|
860
|
+
}
|
861
|
+
};
|
862
|
+
|
863
|
+
this._onRead = function()
|
864
|
+
{
|
865
|
+
if (this._handle.paused()) {
|
866
|
+
// the writeable consumer can handle more data
|
867
|
+
// so resume the chunk parsing
|
868
|
+
this._handle.resume();
|
869
|
+
}
|
870
|
+
};
|
871
|
+
|
872
|
+
this._onWrite = function(chunk, encoding, callback)
|
873
|
+
{
|
874
|
+
this._addToParseQueue(chunk, callback);
|
875
|
+
};
|
876
|
+
|
877
|
+
this._onWriteComplete = function()
|
878
|
+
{
|
879
|
+
writeStreamHasFinished = true;
|
880
|
+
// have to write empty string
|
881
|
+
// so parser knows its done
|
882
|
+
this._addToParseQueue('');
|
883
|
+
};
|
884
|
+
|
885
|
+
this.getStream = function()
|
886
|
+
{
|
887
|
+
return stream;
|
888
|
+
};
|
889
|
+
stream = new Duplex({
|
890
|
+
readableObjectMode: true,
|
891
|
+
decodeStrings: false,
|
892
|
+
read: bindFunction(this._onRead, this),
|
893
|
+
write: bindFunction(this._onWrite, this)
|
894
|
+
});
|
895
|
+
stream.once('finish', bindFunction(this._onWriteComplete, this));
|
896
|
+
}
|
897
|
+
if (typeof PAPA_BROWSER_CONTEXT === 'undefined') {
|
898
|
+
DuplexStreamStreamer.prototype = Object.create(ChunkStreamer.prototype);
|
899
|
+
DuplexStreamStreamer.prototype.constructor = DuplexStreamStreamer;
|
900
|
+
}
|
901
|
+
|
902
|
+
|
903
|
+
// Use one ParserHandle per entire CSV file or string
|
904
|
+
function ParserHandle(_config)
|
905
|
+
{
|
906
|
+
// One goal is to minimize the use of regular expressions...
|
907
|
+
var MAX_FLOAT = Math.pow(2, 53);
|
908
|
+
var MIN_FLOAT = -MAX_FLOAT;
|
909
|
+
var FLOAT = /^\s*-?(\d+\.?|\.\d+|\d+\.\d+)([eE][-+]?\d+)?\s*$/;
|
910
|
+
var ISO_DATE = /^((\d{4}-[01]\d-[0-3]\dT[0-2]\d:[0-5]\d:[0-5]\d\.\d+([+-][0-2]\d:[0-5]\d|Z))|(\d{4}-[01]\d-[0-3]\dT[0-2]\d:[0-5]\d:[0-5]\d([+-][0-2]\d:[0-5]\d|Z))|(\d{4}-[01]\d-[0-3]\dT[0-2]\d:[0-5]\d([+-][0-2]\d:[0-5]\d|Z)))$/;
|
911
|
+
var self = this;
|
912
|
+
var _stepCounter = 0; // Number of times step was called (number of rows parsed)
|
913
|
+
var _rowCounter = 0; // Number of rows that have been parsed so far
|
914
|
+
var _input; // The input being parsed
|
915
|
+
var _parser; // The core parser being used
|
916
|
+
var _paused = false; // Whether we are paused or not
|
917
|
+
var _aborted = false; // Whether the parser has aborted or not
|
918
|
+
var _delimiterError; // Temporary state between delimiter detection and processing results
|
919
|
+
var _fields = []; // Fields are from the header row of the input, if there is one
|
920
|
+
var _results = { // The last results returned from the parser
|
921
|
+
data: [],
|
922
|
+
errors: [],
|
923
|
+
meta: {}
|
924
|
+
};
|
925
|
+
|
926
|
+
if (isFunction(_config.step))
|
927
|
+
{
|
928
|
+
var userStep = _config.step;
|
929
|
+
_config.step = function(results)
|
930
|
+
{
|
931
|
+
_results = results;
|
932
|
+
|
933
|
+
if (needsHeaderRow())
|
934
|
+
processResults();
|
935
|
+
else // only call user's step function after header row
|
936
|
+
{
|
937
|
+
processResults();
|
938
|
+
|
939
|
+
// It's possbile that this line was empty and there's no row here after all
|
940
|
+
if (_results.data.length === 0)
|
941
|
+
return;
|
942
|
+
|
943
|
+
_stepCounter += results.data.length;
|
944
|
+
if (_config.preview && _stepCounter > _config.preview)
|
945
|
+
_parser.abort();
|
946
|
+
else {
|
947
|
+
_results.data = _results.data[0];
|
948
|
+
userStep(_results, self);
|
949
|
+
}
|
950
|
+
}
|
951
|
+
};
|
952
|
+
}
|
953
|
+
|
954
|
+
/**
|
955
|
+
* Parses input. Most users won't need, and shouldn't mess with, the baseIndex
|
956
|
+
* and ignoreLastRow parameters. They are used by streamers (wrapper functions)
|
957
|
+
* when an input comes in multiple chunks, like from a file.
|
958
|
+
*/
|
959
|
+
this.parse = function(input, baseIndex, ignoreLastRow)
|
960
|
+
{
|
961
|
+
var quoteChar = _config.quoteChar || '"';
|
962
|
+
if (!_config.newline)
|
963
|
+
_config.newline = guessLineEndings(input, quoteChar);
|
964
|
+
|
965
|
+
_delimiterError = false;
|
966
|
+
if (!_config.delimiter)
|
967
|
+
{
|
968
|
+
var delimGuess = guessDelimiter(input, _config.newline, _config.skipEmptyLines, _config.comments, _config.delimitersToGuess);
|
969
|
+
if (delimGuess.successful)
|
970
|
+
_config.delimiter = delimGuess.bestDelimiter;
|
971
|
+
else
|
972
|
+
{
|
973
|
+
_delimiterError = true; // add error after parsing (otherwise it would be overwritten)
|
974
|
+
_config.delimiter = Papa.DefaultDelimiter;
|
975
|
+
}
|
976
|
+
_results.meta.delimiter = _config.delimiter;
|
977
|
+
}
|
978
|
+
else if(isFunction(_config.delimiter))
|
979
|
+
{
|
980
|
+
_config.delimiter = _config.delimiter(input);
|
981
|
+
_results.meta.delimiter = _config.delimiter;
|
982
|
+
}
|
983
|
+
|
984
|
+
var parserConfig = copy(_config);
|
985
|
+
if (_config.preview && _config.header)
|
986
|
+
parserConfig.preview++; // to compensate for header row
|
987
|
+
|
988
|
+
_input = input;
|
989
|
+
_parser = new Parser(parserConfig);
|
990
|
+
_results = _parser.parse(_input, baseIndex, ignoreLastRow);
|
991
|
+
processResults();
|
992
|
+
return _paused ? { meta: { paused: true } } : (_results || { meta: { paused: false } });
|
993
|
+
};
|
994
|
+
|
995
|
+
this.paused = function()
|
996
|
+
{
|
997
|
+
return _paused;
|
998
|
+
};
|
999
|
+
|
1000
|
+
this.pause = function()
|
1001
|
+
{
|
1002
|
+
_paused = true;
|
1003
|
+
_parser.abort();
|
1004
|
+
|
1005
|
+
// If it is streaming via "chunking", the reader will start appending correctly already so no need to substring,
|
1006
|
+
// otherwise we can get duplicate content within a row
|
1007
|
+
_input = isFunction(_config.chunk) ? "" : _input.substring(_parser.getCharIndex());
|
1008
|
+
};
|
1009
|
+
|
1010
|
+
this.resume = function()
|
1011
|
+
{
|
1012
|
+
if(self.streamer._halted) {
|
1013
|
+
_paused = false;
|
1014
|
+
self.streamer.parseChunk(_input, true);
|
1015
|
+
} else {
|
1016
|
+
// Bugfix: #636 In case the processing hasn't halted yet
|
1017
|
+
// wait for it to halt in order to resume
|
1018
|
+
setTimeout(self.resume, 3);
|
1019
|
+
}
|
1020
|
+
};
|
1021
|
+
|
1022
|
+
this.aborted = function()
|
1023
|
+
{
|
1024
|
+
return _aborted;
|
1025
|
+
};
|
1026
|
+
|
1027
|
+
this.abort = function()
|
1028
|
+
{
|
1029
|
+
_aborted = true;
|
1030
|
+
_parser.abort();
|
1031
|
+
_results.meta.aborted = true;
|
1032
|
+
if (isFunction(_config.complete))
|
1033
|
+
_config.complete(_results);
|
1034
|
+
_input = '';
|
1035
|
+
};
|
1036
|
+
|
1037
|
+
function testEmptyLine(s) {
|
1038
|
+
return _config.skipEmptyLines === 'greedy' ? s.join('').trim() === '' : s.length === 1 && s[0].length === 0;
|
1039
|
+
}
|
1040
|
+
|
1041
|
+
function testFloat(s) {
|
1042
|
+
if (FLOAT.test(s)) {
|
1043
|
+
var floatValue = parseFloat(s);
|
1044
|
+
if (floatValue > MIN_FLOAT && floatValue < MAX_FLOAT) {
|
1045
|
+
return true;
|
1046
|
+
}
|
1047
|
+
}
|
1048
|
+
return false;
|
1049
|
+
}
|
1050
|
+
|
1051
|
+
function processResults()
|
1052
|
+
{
|
1053
|
+
if (_results && _delimiterError)
|
1054
|
+
{
|
1055
|
+
addError('Delimiter', 'UndetectableDelimiter', 'Unable to auto-detect delimiting character; defaulted to \'' + Papa.DefaultDelimiter + '\'');
|
1056
|
+
_delimiterError = false;
|
1057
|
+
}
|
1058
|
+
|
1059
|
+
if (_config.skipEmptyLines)
|
1060
|
+
{
|
1061
|
+
_results.data = _results.data.filter(function(d) {
|
1062
|
+
return !testEmptyLine(d);
|
1063
|
+
});
|
1064
|
+
}
|
1065
|
+
|
1066
|
+
if (needsHeaderRow())
|
1067
|
+
fillHeaderFields();
|
1068
|
+
|
1069
|
+
return applyHeaderAndDynamicTypingAndTransformation();
|
1070
|
+
}
|
1071
|
+
|
1072
|
+
function needsHeaderRow()
|
1073
|
+
{
|
1074
|
+
return _config.header && _fields.length === 0;
|
1075
|
+
}
|
1076
|
+
|
1077
|
+
function fillHeaderFields()
|
1078
|
+
{
|
1079
|
+
if (!_results)
|
1080
|
+
return;
|
1081
|
+
|
1082
|
+
function addHeader(header, i)
|
1083
|
+
{
|
1084
|
+
if (isFunction(_config.transformHeader))
|
1085
|
+
header = _config.transformHeader(header, i);
|
1086
|
+
|
1087
|
+
_fields.push(header);
|
1088
|
+
}
|
1089
|
+
|
1090
|
+
if (Array.isArray(_results.data[0]))
|
1091
|
+
{
|
1092
|
+
for (var i = 0; needsHeaderRow() && i < _results.data.length; i++)
|
1093
|
+
_results.data[i].forEach(addHeader);
|
1094
|
+
|
1095
|
+
_results.data.splice(0, 1);
|
1096
|
+
}
|
1097
|
+
// if _results.data[0] is not an array, we are in a step where _results.data is the row.
|
1098
|
+
else
|
1099
|
+
_results.data.forEach(addHeader);
|
1100
|
+
}
|
1101
|
+
|
1102
|
+
function shouldApplyDynamicTyping(field) {
|
1103
|
+
// Cache function values to avoid calling it for each row
|
1104
|
+
if (_config.dynamicTypingFunction && _config.dynamicTyping[field] === undefined) {
|
1105
|
+
_config.dynamicTyping[field] = _config.dynamicTypingFunction(field);
|
1106
|
+
}
|
1107
|
+
return (_config.dynamicTyping[field] || _config.dynamicTyping) === true;
|
1108
|
+
}
|
1109
|
+
|
1110
|
+
function parseDynamic(field, value)
|
1111
|
+
{
|
1112
|
+
if (shouldApplyDynamicTyping(field))
|
1113
|
+
{
|
1114
|
+
if (value === 'true' || value === 'TRUE')
|
1115
|
+
return true;
|
1116
|
+
else if (value === 'false' || value === 'FALSE')
|
1117
|
+
return false;
|
1118
|
+
else if (testFloat(value))
|
1119
|
+
return parseFloat(value);
|
1120
|
+
else if (ISO_DATE.test(value))
|
1121
|
+
return new Date(value);
|
1122
|
+
else
|
1123
|
+
return (value === '' ? null : value);
|
1124
|
+
}
|
1125
|
+
return value;
|
1126
|
+
}
|
1127
|
+
|
1128
|
+
function applyHeaderAndDynamicTypingAndTransformation()
|
1129
|
+
{
|
1130
|
+
if (!_results || (!_config.header && !_config.dynamicTyping && !_config.transform))
|
1131
|
+
return _results;
|
1132
|
+
|
1133
|
+
function processRow(rowSource, i)
|
1134
|
+
{
|
1135
|
+
var row = _config.header ? {} : [];
|
1136
|
+
|
1137
|
+
var j;
|
1138
|
+
for (j = 0; j < rowSource.length; j++)
|
1139
|
+
{
|
1140
|
+
var field = j;
|
1141
|
+
var value = rowSource[j];
|
1142
|
+
|
1143
|
+
if (_config.header)
|
1144
|
+
field = j >= _fields.length ? '__parsed_extra' : _fields[j];
|
1145
|
+
|
1146
|
+
if (_config.transform)
|
1147
|
+
value = _config.transform(value,field);
|
1148
|
+
|
1149
|
+
value = parseDynamic(field, value);
|
1150
|
+
|
1151
|
+
if (field === '__parsed_extra')
|
1152
|
+
{
|
1153
|
+
row[field] = row[field] || [];
|
1154
|
+
row[field].push(value);
|
1155
|
+
}
|
1156
|
+
else
|
1157
|
+
row[field] = value;
|
1158
|
+
}
|
1159
|
+
|
1160
|
+
|
1161
|
+
if (_config.header)
|
1162
|
+
{
|
1163
|
+
if (j > _fields.length)
|
1164
|
+
addError('FieldMismatch', 'TooManyFields', 'Too many fields: expected ' + _fields.length + ' fields but parsed ' + j, _rowCounter + i);
|
1165
|
+
else if (j < _fields.length)
|
1166
|
+
addError('FieldMismatch', 'TooFewFields', 'Too few fields: expected ' + _fields.length + ' fields but parsed ' + j, _rowCounter + i);
|
1167
|
+
}
|
1168
|
+
|
1169
|
+
return row;
|
1170
|
+
}
|
1171
|
+
|
1172
|
+
var incrementBy = 1;
|
1173
|
+
if (!_results.data.length || Array.isArray(_results.data[0]))
|
1174
|
+
{
|
1175
|
+
_results.data = _results.data.map(processRow);
|
1176
|
+
incrementBy = _results.data.length;
|
1177
|
+
}
|
1178
|
+
else
|
1179
|
+
_results.data = processRow(_results.data, 0);
|
1180
|
+
|
1181
|
+
|
1182
|
+
if (_config.header && _results.meta)
|
1183
|
+
_results.meta.fields = _fields;
|
1184
|
+
|
1185
|
+
_rowCounter += incrementBy;
|
1186
|
+
return _results;
|
1187
|
+
}
|
1188
|
+
|
1189
|
+
function guessDelimiter(input, newline, skipEmptyLines, comments, delimitersToGuess) {
|
1190
|
+
var bestDelim, bestDelta, fieldCountPrevRow, maxFieldCount;
|
1191
|
+
|
1192
|
+
delimitersToGuess = delimitersToGuess || [',', '\t', '|', ';', Papa.RECORD_SEP, Papa.UNIT_SEP];
|
1193
|
+
|
1194
|
+
for (var i = 0; i < delimitersToGuess.length; i++) {
|
1195
|
+
var delim = delimitersToGuess[i];
|
1196
|
+
var delta = 0, avgFieldCount = 0, emptyLinesCount = 0;
|
1197
|
+
fieldCountPrevRow = undefined;
|
1198
|
+
|
1199
|
+
var preview = new Parser({
|
1200
|
+
comments: comments,
|
1201
|
+
delimiter: delim,
|
1202
|
+
newline: newline,
|
1203
|
+
preview: 10
|
1204
|
+
}).parse(input);
|
1205
|
+
|
1206
|
+
for (var j = 0; j < preview.data.length; j++) {
|
1207
|
+
if (skipEmptyLines && testEmptyLine(preview.data[j])) {
|
1208
|
+
emptyLinesCount++;
|
1209
|
+
continue;
|
1210
|
+
}
|
1211
|
+
var fieldCount = preview.data[j].length;
|
1212
|
+
avgFieldCount += fieldCount;
|
1213
|
+
|
1214
|
+
if (typeof fieldCountPrevRow === 'undefined') {
|
1215
|
+
fieldCountPrevRow = fieldCount;
|
1216
|
+
continue;
|
1217
|
+
}
|
1218
|
+
else if (fieldCount > 0) {
|
1219
|
+
delta += Math.abs(fieldCount - fieldCountPrevRow);
|
1220
|
+
fieldCountPrevRow = fieldCount;
|
1221
|
+
}
|
1222
|
+
}
|
1223
|
+
|
1224
|
+
if (preview.data.length > 0)
|
1225
|
+
avgFieldCount /= (preview.data.length - emptyLinesCount);
|
1226
|
+
|
1227
|
+
if ((typeof bestDelta === 'undefined' || delta <= bestDelta)
|
1228
|
+
&& (typeof maxFieldCount === 'undefined' || avgFieldCount > maxFieldCount) && avgFieldCount > 1.99) {
|
1229
|
+
bestDelta = delta;
|
1230
|
+
bestDelim = delim;
|
1231
|
+
maxFieldCount = avgFieldCount;
|
1232
|
+
}
|
1233
|
+
}
|
1234
|
+
|
1235
|
+
_config.delimiter = bestDelim;
|
1236
|
+
|
1237
|
+
return {
|
1238
|
+
successful: !!bestDelim,
|
1239
|
+
bestDelimiter: bestDelim
|
1240
|
+
};
|
1241
|
+
}
|
1242
|
+
|
1243
|
+
function guessLineEndings(input, quoteChar)
|
1244
|
+
{
|
1245
|
+
input = input.substring(0, 1024 * 1024); // max length 1 MB
|
1246
|
+
// Replace all the text inside quotes
|
1247
|
+
var re = new RegExp(escapeRegExp(quoteChar) + '([^]*?)' + escapeRegExp(quoteChar), 'gm');
|
1248
|
+
input = input.replace(re, '');
|
1249
|
+
|
1250
|
+
var r = input.split('\r');
|
1251
|
+
|
1252
|
+
var n = input.split('\n');
|
1253
|
+
|
1254
|
+
var nAppearsFirst = (n.length > 1 && n[0].length < r[0].length);
|
1255
|
+
|
1256
|
+
if (r.length === 1 || nAppearsFirst)
|
1257
|
+
return '\n';
|
1258
|
+
|
1259
|
+
var numWithN = 0;
|
1260
|
+
for (var i = 0; i < r.length; i++)
|
1261
|
+
{
|
1262
|
+
if (r[i][0] === '\n')
|
1263
|
+
numWithN++;
|
1264
|
+
}
|
1265
|
+
|
1266
|
+
return numWithN >= r.length / 2 ? '\r\n' : '\r';
|
1267
|
+
}
|
1268
|
+
|
1269
|
+
function addError(type, code, msg, row)
|
1270
|
+
{
|
1271
|
+
var error = {
|
1272
|
+
type: type,
|
1273
|
+
code: code,
|
1274
|
+
message: msg
|
1275
|
+
};
|
1276
|
+
if(row !== undefined) {
|
1277
|
+
error.row = row;
|
1278
|
+
}
|
1279
|
+
_results.errors.push(error);
|
1280
|
+
}
|
1281
|
+
}
|
1282
|
+
|
1283
|
+
/** https://developer.mozilla.org/en-US/docs/Web/JavaScript/Guide/Regular_Expressions */
|
1284
|
+
function escapeRegExp(string)
|
1285
|
+
{
|
1286
|
+
return string.replace(/[.*+?^${}()|[\]\\]/g, '\\$&'); // $& means the whole matched string
|
1287
|
+
}
|
1288
|
+
|
1289
|
+
/** The core parser implements speedy and correct CSV parsing */
|
1290
|
+
function Parser(config)
|
1291
|
+
{
|
1292
|
+
// Unpack the config object
|
1293
|
+
config = config || {};
|
1294
|
+
var delim = config.delimiter;
|
1295
|
+
var newline = config.newline;
|
1296
|
+
var comments = config.comments;
|
1297
|
+
var step = config.step;
|
1298
|
+
var preview = config.preview;
|
1299
|
+
var fastMode = config.fastMode;
|
1300
|
+
var quoteChar;
|
1301
|
+
var renamedHeaders = null;
|
1302
|
+
|
1303
|
+
if (config.quoteChar === undefined || config.quoteChar === null) {
|
1304
|
+
quoteChar = '"';
|
1305
|
+
} else {
|
1306
|
+
quoteChar = config.quoteChar;
|
1307
|
+
}
|
1308
|
+
var escapeChar = quoteChar;
|
1309
|
+
if (config.escapeChar !== undefined) {
|
1310
|
+
escapeChar = config.escapeChar;
|
1311
|
+
}
|
1312
|
+
|
1313
|
+
// Delimiter must be valid
|
1314
|
+
if (typeof delim !== 'string'
|
1315
|
+
|| Papa.BAD_DELIMITERS.indexOf(delim) > -1)
|
1316
|
+
delim = ',';
|
1317
|
+
|
1318
|
+
// Comment character must be valid
|
1319
|
+
if (comments === delim)
|
1320
|
+
throw new Error('Comment character same as delimiter');
|
1321
|
+
else if (comments === true)
|
1322
|
+
comments = '#';
|
1323
|
+
else if (typeof comments !== 'string'
|
1324
|
+
|| Papa.BAD_DELIMITERS.indexOf(comments) > -1)
|
1325
|
+
comments = false;
|
1326
|
+
|
1327
|
+
// Newline must be valid: \r, \n, or \r\n
|
1328
|
+
if (newline !== '\n' && newline !== '\r' && newline !== '\r\n')
|
1329
|
+
newline = '\n';
|
1330
|
+
|
1331
|
+
// We're gonna need these at the Parser scope
|
1332
|
+
var cursor = 0;
|
1333
|
+
var aborted = false;
|
1334
|
+
|
1335
|
+
this.parse = function(input, baseIndex, ignoreLastRow)
|
1336
|
+
{
|
1337
|
+
// For some reason, in Chrome, this speeds things up (!?)
|
1338
|
+
if (typeof input !== 'string')
|
1339
|
+
throw new Error('Input must be a string');
|
1340
|
+
|
1341
|
+
// We don't need to compute some of these every time parse() is called,
|
1342
|
+
// but having them in a more local scope seems to perform better
|
1343
|
+
var inputLen = input.length,
|
1344
|
+
delimLen = delim.length,
|
1345
|
+
newlineLen = newline.length,
|
1346
|
+
commentsLen = comments.length;
|
1347
|
+
var stepIsFunction = isFunction(step);
|
1348
|
+
|
1349
|
+
// Establish starting state
|
1350
|
+
cursor = 0;
|
1351
|
+
var data = [], errors = [], row = [], lastCursor = 0;
|
1352
|
+
|
1353
|
+
if (!input)
|
1354
|
+
return returnable();
|
1355
|
+
|
1356
|
+
// Rename headers if there are duplicates
|
1357
|
+
var firstLine;
|
1358
|
+
if (config.header && !baseIndex)
|
1359
|
+
{
|
1360
|
+
firstLine = input.split(newline)[0];
|
1361
|
+
var headers = firstLine.split(delim);
|
1362
|
+
var separator = '_';
|
1363
|
+
var headerMap = new Set();
|
1364
|
+
var headerCount = {};
|
1365
|
+
var duplicateHeaders = false;
|
1366
|
+
|
1367
|
+
// Using old-style 'for' loop to avoid prototype pollution that would be picked up with 'var j in headers'
|
1368
|
+
for (var j = 0; j < headers.length; j++) {
|
1369
|
+
var header = headers[j];
|
1370
|
+
if (isFunction(config.transformHeader))
|
1371
|
+
header = config.transformHeader(header, j);
|
1372
|
+
var headerName = header;
|
1373
|
+
|
1374
|
+
var count = headerCount[header] || 0;
|
1375
|
+
if (count > 0) {
|
1376
|
+
duplicateHeaders = true;
|
1377
|
+
headerName = header + separator + count;
|
1378
|
+
// Initialise the variable if it hasn't been.
|
1379
|
+
if (renamedHeaders === null) {
|
1380
|
+
renamedHeaders = {};
|
1381
|
+
}
|
1382
|
+
}
|
1383
|
+
headerCount[header] = count + 1;
|
1384
|
+
// In case it already exists, we add more separators
|
1385
|
+
while (headerMap.has(headerName)) {
|
1386
|
+
headerName = headerName + separator + count;
|
1387
|
+
}
|
1388
|
+
headerMap.add(headerName);
|
1389
|
+
if (count > 0) {
|
1390
|
+
renamedHeaders[headerName] = header;
|
1391
|
+
}
|
1392
|
+
}
|
1393
|
+
if (duplicateHeaders) {
|
1394
|
+
var editedInput = input.split(newline);
|
1395
|
+
editedInput[0] = Array.from(headerMap).join(delim);
|
1396
|
+
input = editedInput.join(newline);
|
1397
|
+
}
|
1398
|
+
}
|
1399
|
+
if (fastMode || (fastMode !== false && input.indexOf(quoteChar) === -1))
|
1400
|
+
{
|
1401
|
+
var rows = input.split(newline);
|
1402
|
+
for (var i = 0; i < rows.length; i++)
|
1403
|
+
{
|
1404
|
+
row = rows[i];
|
1405
|
+
// use firstline as row length may be changed due to duplicated headers
|
1406
|
+
if (i === 0 && firstLine !== undefined) {
|
1407
|
+
cursor += firstLine.length;
|
1408
|
+
}else{
|
1409
|
+
cursor += row.length;
|
1410
|
+
}
|
1411
|
+
if (i !== rows.length - 1)
|
1412
|
+
cursor += newline.length;
|
1413
|
+
else if (ignoreLastRow)
|
1414
|
+
return returnable();
|
1415
|
+
if (comments && row.substring(0, commentsLen) === comments)
|
1416
|
+
continue;
|
1417
|
+
if (stepIsFunction)
|
1418
|
+
{
|
1419
|
+
data = [];
|
1420
|
+
pushRow(row.split(delim));
|
1421
|
+
doStep();
|
1422
|
+
if (aborted)
|
1423
|
+
return returnable();
|
1424
|
+
}
|
1425
|
+
else
|
1426
|
+
pushRow(row.split(delim));
|
1427
|
+
if (preview && i >= preview)
|
1428
|
+
{
|
1429
|
+
data = data.slice(0, preview);
|
1430
|
+
return returnable(true);
|
1431
|
+
}
|
1432
|
+
}
|
1433
|
+
return returnable();
|
1434
|
+
}
|
1435
|
+
|
1436
|
+
var nextDelim = input.indexOf(delim, cursor);
|
1437
|
+
var nextNewline = input.indexOf(newline, cursor);
|
1438
|
+
var quoteCharRegex = new RegExp(escapeRegExp(escapeChar) + escapeRegExp(quoteChar), 'g');
|
1439
|
+
var quoteSearch = input.indexOf(quoteChar, cursor);
|
1440
|
+
|
1441
|
+
// Parser loop
|
1442
|
+
for (;;)
|
1443
|
+
{
|
1444
|
+
// Field has opening quote
|
1445
|
+
if (input[cursor] === quoteChar)
|
1446
|
+
{
|
1447
|
+
// Start our search for the closing quote where the cursor is
|
1448
|
+
quoteSearch = cursor;
|
1449
|
+
|
1450
|
+
// Skip the opening quote
|
1451
|
+
cursor++;
|
1452
|
+
|
1453
|
+
for (;;)
|
1454
|
+
{
|
1455
|
+
// Find closing quote
|
1456
|
+
quoteSearch = input.indexOf(quoteChar, quoteSearch + 1);
|
1457
|
+
|
1458
|
+
//No other quotes are found - no other delimiters
|
1459
|
+
if (quoteSearch === -1)
|
1460
|
+
{
|
1461
|
+
if (!ignoreLastRow) {
|
1462
|
+
// No closing quote... what a pity
|
1463
|
+
errors.push({
|
1464
|
+
type: 'Quotes',
|
1465
|
+
code: 'MissingQuotes',
|
1466
|
+
message: 'Quoted field unterminated',
|
1467
|
+
row: data.length, // row has yet to be inserted
|
1468
|
+
index: cursor
|
1469
|
+
});
|
1470
|
+
}
|
1471
|
+
return finish();
|
1472
|
+
}
|
1473
|
+
|
1474
|
+
// Closing quote at EOF
|
1475
|
+
if (quoteSearch === inputLen - 1)
|
1476
|
+
{
|
1477
|
+
var value = input.substring(cursor, quoteSearch).replace(quoteCharRegex, quoteChar);
|
1478
|
+
return finish(value);
|
1479
|
+
}
|
1480
|
+
|
1481
|
+
// If this quote is escaped, it's part of the data; skip it
|
1482
|
+
// If the quote character is the escape character, then check if the next character is the escape character
|
1483
|
+
if (quoteChar === escapeChar && input[quoteSearch + 1] === escapeChar)
|
1484
|
+
{
|
1485
|
+
quoteSearch++;
|
1486
|
+
continue;
|
1487
|
+
}
|
1488
|
+
|
1489
|
+
// If the quote character is not the escape character, then check if the previous character was the escape character
|
1490
|
+
if (quoteChar !== escapeChar && quoteSearch !== 0 && input[quoteSearch - 1] === escapeChar)
|
1491
|
+
{
|
1492
|
+
continue;
|
1493
|
+
}
|
1494
|
+
|
1495
|
+
if(nextDelim !== -1 && nextDelim < (quoteSearch + 1)) {
|
1496
|
+
nextDelim = input.indexOf(delim, (quoteSearch + 1));
|
1497
|
+
}
|
1498
|
+
if(nextNewline !== -1 && nextNewline < (quoteSearch + 1)) {
|
1499
|
+
nextNewline = input.indexOf(newline, (quoteSearch + 1));
|
1500
|
+
}
|
1501
|
+
// Check up to nextDelim or nextNewline, whichever is closest
|
1502
|
+
var checkUpTo = nextNewline === -1 ? nextDelim : Math.min(nextDelim, nextNewline);
|
1503
|
+
var spacesBetweenQuoteAndDelimiter = extraSpaces(checkUpTo);
|
1504
|
+
|
1505
|
+
// Closing quote followed by delimiter or 'unnecessary spaces + delimiter'
|
1506
|
+
if (input.substr(quoteSearch + 1 + spacesBetweenQuoteAndDelimiter, delimLen) === delim)
|
1507
|
+
{
|
1508
|
+
row.push(input.substring(cursor, quoteSearch).replace(quoteCharRegex, quoteChar));
|
1509
|
+
cursor = quoteSearch + 1 + spacesBetweenQuoteAndDelimiter + delimLen;
|
1510
|
+
|
1511
|
+
// If char after following delimiter is not quoteChar, we find next quote char position
|
1512
|
+
if (input[quoteSearch + 1 + spacesBetweenQuoteAndDelimiter + delimLen] !== quoteChar)
|
1513
|
+
{
|
1514
|
+
quoteSearch = input.indexOf(quoteChar, cursor);
|
1515
|
+
}
|
1516
|
+
nextDelim = input.indexOf(delim, cursor);
|
1517
|
+
nextNewline = input.indexOf(newline, cursor);
|
1518
|
+
break;
|
1519
|
+
}
|
1520
|
+
|
1521
|
+
var spacesBetweenQuoteAndNewLine = extraSpaces(nextNewline);
|
1522
|
+
|
1523
|
+
// Closing quote followed by newline or 'unnecessary spaces + newLine'
|
1524
|
+
if (input.substring(quoteSearch + 1 + spacesBetweenQuoteAndNewLine, quoteSearch + 1 + spacesBetweenQuoteAndNewLine + newlineLen) === newline)
|
1525
|
+
{
|
1526
|
+
row.push(input.substring(cursor, quoteSearch).replace(quoteCharRegex, quoteChar));
|
1527
|
+
saveRow(quoteSearch + 1 + spacesBetweenQuoteAndNewLine + newlineLen);
|
1528
|
+
nextDelim = input.indexOf(delim, cursor); // because we may have skipped the nextDelim in the quoted field
|
1529
|
+
quoteSearch = input.indexOf(quoteChar, cursor); // we search for first quote in next line
|
1530
|
+
|
1531
|
+
if (stepIsFunction)
|
1532
|
+
{
|
1533
|
+
doStep();
|
1534
|
+
if (aborted)
|
1535
|
+
return returnable();
|
1536
|
+
}
|
1537
|
+
|
1538
|
+
if (preview && data.length >= preview)
|
1539
|
+
return returnable(true);
|
1540
|
+
|
1541
|
+
break;
|
1542
|
+
}
|
1543
|
+
|
1544
|
+
|
1545
|
+
// Checks for valid closing quotes are complete (escaped quotes or quote followed by EOF/delimiter/newline) -- assume these quotes are part of an invalid text string
|
1546
|
+
errors.push({
|
1547
|
+
type: 'Quotes',
|
1548
|
+
code: 'InvalidQuotes',
|
1549
|
+
message: 'Trailing quote on quoted field is malformed',
|
1550
|
+
row: data.length, // row has yet to be inserted
|
1551
|
+
index: cursor
|
1552
|
+
});
|
1553
|
+
|
1554
|
+
quoteSearch++;
|
1555
|
+
continue;
|
1556
|
+
|
1557
|
+
}
|
1558
|
+
|
1559
|
+
continue;
|
1560
|
+
}
|
1561
|
+
|
1562
|
+
// Comment found at start of new line
|
1563
|
+
if (comments && row.length === 0 && input.substring(cursor, cursor + commentsLen) === comments)
|
1564
|
+
{
|
1565
|
+
if (nextNewline === -1) // Comment ends at EOF
|
1566
|
+
return returnable();
|
1567
|
+
cursor = nextNewline + newlineLen;
|
1568
|
+
nextNewline = input.indexOf(newline, cursor);
|
1569
|
+
nextDelim = input.indexOf(delim, cursor);
|
1570
|
+
continue;
|
1571
|
+
}
|
1572
|
+
|
1573
|
+
// Next delimiter comes before next newline, so we've reached end of field
|
1574
|
+
if (nextDelim !== -1 && (nextDelim < nextNewline || nextNewline === -1))
|
1575
|
+
{
|
1576
|
+
row.push(input.substring(cursor, nextDelim));
|
1577
|
+
cursor = nextDelim + delimLen;
|
1578
|
+
// we look for next delimiter char
|
1579
|
+
nextDelim = input.indexOf(delim, cursor);
|
1580
|
+
continue;
|
1581
|
+
}
|
1582
|
+
|
1583
|
+
// End of row
|
1584
|
+
if (nextNewline !== -1)
|
1585
|
+
{
|
1586
|
+
row.push(input.substring(cursor, nextNewline));
|
1587
|
+
saveRow(nextNewline + newlineLen);
|
1588
|
+
|
1589
|
+
if (stepIsFunction)
|
1590
|
+
{
|
1591
|
+
doStep();
|
1592
|
+
if (aborted)
|
1593
|
+
return returnable();
|
1594
|
+
}
|
1595
|
+
|
1596
|
+
if (preview && data.length >= preview)
|
1597
|
+
return returnable(true);
|
1598
|
+
|
1599
|
+
continue;
|
1600
|
+
}
|
1601
|
+
|
1602
|
+
break;
|
1603
|
+
}
|
1604
|
+
|
1605
|
+
|
1606
|
+
return finish();
|
1607
|
+
|
1608
|
+
|
1609
|
+
function pushRow(row)
|
1610
|
+
{
|
1611
|
+
data.push(row);
|
1612
|
+
lastCursor = cursor;
|
1613
|
+
}
|
1614
|
+
|
1615
|
+
/**
|
1616
|
+
* checks if there are extra spaces after closing quote and given index without any text
|
1617
|
+
* if Yes, returns the number of spaces
|
1618
|
+
*/
|
1619
|
+
function extraSpaces(index) {
|
1620
|
+
var spaceLength = 0;
|
1621
|
+
if (index !== -1) {
|
1622
|
+
var textBetweenClosingQuoteAndIndex = input.substring(quoteSearch + 1, index);
|
1623
|
+
if (textBetweenClosingQuoteAndIndex && textBetweenClosingQuoteAndIndex.trim() === '') {
|
1624
|
+
spaceLength = textBetweenClosingQuoteAndIndex.length;
|
1625
|
+
}
|
1626
|
+
}
|
1627
|
+
return spaceLength;
|
1628
|
+
}
|
1629
|
+
|
1630
|
+
/**
|
1631
|
+
* Appends the remaining input from cursor to the end into
|
1632
|
+
* row, saves the row, calls step, and returns the results.
|
1633
|
+
*/
|
1634
|
+
function finish(value)
|
1635
|
+
{
|
1636
|
+
if (ignoreLastRow)
|
1637
|
+
return returnable();
|
1638
|
+
if (typeof value === 'undefined')
|
1639
|
+
value = input.substring(cursor);
|
1640
|
+
row.push(value);
|
1641
|
+
cursor = inputLen; // important in case parsing is paused
|
1642
|
+
pushRow(row);
|
1643
|
+
if (stepIsFunction)
|
1644
|
+
doStep();
|
1645
|
+
return returnable();
|
1646
|
+
}
|
1647
|
+
|
1648
|
+
/**
|
1649
|
+
* Appends the current row to the results. It sets the cursor
|
1650
|
+
* to newCursor and finds the nextNewline. The caller should
|
1651
|
+
* take care to execute user's step function and check for
|
1652
|
+
* preview and end parsing if necessary.
|
1653
|
+
*/
|
1654
|
+
function saveRow(newCursor)
|
1655
|
+
{
|
1656
|
+
cursor = newCursor;
|
1657
|
+
pushRow(row);
|
1658
|
+
row = [];
|
1659
|
+
nextNewline = input.indexOf(newline, cursor);
|
1660
|
+
}
|
1661
|
+
|
1662
|
+
/** Returns an object with the results, errors, and meta. */
|
1663
|
+
function returnable(stopped)
|
1664
|
+
{
|
1665
|
+
return {
|
1666
|
+
data: data,
|
1667
|
+
errors: errors,
|
1668
|
+
meta: {
|
1669
|
+
delimiter: delim,
|
1670
|
+
linebreak: newline,
|
1671
|
+
aborted: aborted,
|
1672
|
+
truncated: !!stopped,
|
1673
|
+
cursor: lastCursor + (baseIndex || 0),
|
1674
|
+
renamedHeaders: renamedHeaders
|
1675
|
+
}
|
1676
|
+
};
|
1677
|
+
}
|
1678
|
+
|
1679
|
+
/** Executes the user's step function and resets data & errors. */
|
1680
|
+
function doStep()
|
1681
|
+
{
|
1682
|
+
step(returnable());
|
1683
|
+
data = [];
|
1684
|
+
errors = [];
|
1685
|
+
}
|
1686
|
+
};
|
1687
|
+
|
1688
|
+
/** Sets the abort flag */
|
1689
|
+
this.abort = function()
|
1690
|
+
{
|
1691
|
+
aborted = true;
|
1692
|
+
};
|
1693
|
+
|
1694
|
+
/** Gets the cursor position */
|
1695
|
+
this.getCharIndex = function()
|
1696
|
+
{
|
1697
|
+
return cursor;
|
1698
|
+
};
|
1699
|
+
}
|
1700
|
+
|
1701
|
+
|
1702
|
+
function newWorker()
|
1703
|
+
{
|
1704
|
+
if (!Papa.WORKERS_SUPPORTED)
|
1705
|
+
return false;
|
1706
|
+
|
1707
|
+
var workerUrl = getWorkerBlob();
|
1708
|
+
var w = new global.Worker(workerUrl);
|
1709
|
+
w.onmessage = mainThreadReceivedMessage;
|
1710
|
+
w.id = workerIdCounter++;
|
1711
|
+
workers[w.id] = w;
|
1712
|
+
return w;
|
1713
|
+
}
|
1714
|
+
|
1715
|
+
/** Callback when main thread receives a message */
|
1716
|
+
function mainThreadReceivedMessage(e)
|
1717
|
+
{
|
1718
|
+
var msg = e.data;
|
1719
|
+
var worker = workers[msg.workerId];
|
1720
|
+
var aborted = false;
|
1721
|
+
|
1722
|
+
if (msg.error)
|
1723
|
+
worker.userError(msg.error, msg.file);
|
1724
|
+
else if (msg.results && msg.results.data)
|
1725
|
+
{
|
1726
|
+
var abort = function() {
|
1727
|
+
aborted = true;
|
1728
|
+
completeWorker(msg.workerId, { data: [], errors: [], meta: { aborted: true } });
|
1729
|
+
};
|
1730
|
+
|
1731
|
+
var handle = {
|
1732
|
+
abort: abort,
|
1733
|
+
pause: notImplemented,
|
1734
|
+
resume: notImplemented
|
1735
|
+
};
|
1736
|
+
|
1737
|
+
if (isFunction(worker.userStep))
|
1738
|
+
{
|
1739
|
+
for (var i = 0; i < msg.results.data.length; i++)
|
1740
|
+
{
|
1741
|
+
worker.userStep({
|
1742
|
+
data: msg.results.data[i],
|
1743
|
+
errors: msg.results.errors,
|
1744
|
+
meta: msg.results.meta
|
1745
|
+
}, handle);
|
1746
|
+
if (aborted)
|
1747
|
+
break;
|
1748
|
+
}
|
1749
|
+
delete msg.results; // free memory ASAP
|
1750
|
+
}
|
1751
|
+
else if (isFunction(worker.userChunk))
|
1752
|
+
{
|
1753
|
+
worker.userChunk(msg.results, handle, msg.file);
|
1754
|
+
delete msg.results;
|
1755
|
+
}
|
1756
|
+
}
|
1757
|
+
|
1758
|
+
if (msg.finished && !aborted)
|
1759
|
+
completeWorker(msg.workerId, msg.results);
|
1760
|
+
}
|
1761
|
+
|
1762
|
+
function completeWorker(workerId, results) {
|
1763
|
+
var worker = workers[workerId];
|
1764
|
+
if (isFunction(worker.userComplete))
|
1765
|
+
worker.userComplete(results);
|
1766
|
+
worker.terminate();
|
1767
|
+
delete workers[workerId];
|
1768
|
+
}
|
1769
|
+
|
1770
|
+
function notImplemented() {
|
1771
|
+
throw new Error('Not implemented.');
|
1772
|
+
}
|
1773
|
+
|
1774
|
+
/** Callback when worker thread receives a message */
|
1775
|
+
function workerThreadReceivedMessage(e)
|
1776
|
+
{
|
1777
|
+
var msg = e.data;
|
1778
|
+
|
1779
|
+
if (typeof Papa.WORKER_ID === 'undefined' && msg)
|
1780
|
+
Papa.WORKER_ID = msg.workerId;
|
1781
|
+
|
1782
|
+
if (typeof msg.input === 'string')
|
1783
|
+
{
|
1784
|
+
global.postMessage({
|
1785
|
+
workerId: Papa.WORKER_ID,
|
1786
|
+
results: Papa.parse(msg.input, msg.config),
|
1787
|
+
finished: true
|
1788
|
+
});
|
1789
|
+
}
|
1790
|
+
else if ((global.File && msg.input instanceof File) || msg.input instanceof Object) // thank you, Safari (see issue #106)
|
1791
|
+
{
|
1792
|
+
var results = Papa.parse(msg.input, msg.config);
|
1793
|
+
if (results)
|
1794
|
+
global.postMessage({
|
1795
|
+
workerId: Papa.WORKER_ID,
|
1796
|
+
results: results,
|
1797
|
+
finished: true
|
1798
|
+
});
|
1799
|
+
}
|
1800
|
+
}
|
1801
|
+
|
1802
|
+
/** Makes a deep copy of an array or object (mostly) */
|
1803
|
+
function copy(obj)
|
1804
|
+
{
|
1805
|
+
if (typeof obj !== 'object' || obj === null)
|
1806
|
+
return obj;
|
1807
|
+
var cpy = Array.isArray(obj) ? [] : {};
|
1808
|
+
for (var key in obj)
|
1809
|
+
cpy[key] = copy(obj[key]);
|
1810
|
+
return cpy;
|
1811
|
+
}
|
1812
|
+
|
1813
|
+
function bindFunction(f, self)
|
1814
|
+
{
|
1815
|
+
return function() { f.apply(self, arguments); };
|
1816
|
+
}
|
1817
|
+
function isFunction(func)
|
1818
|
+
{
|
1819
|
+
return typeof func === 'function';
|
1820
|
+
}
|
1821
|
+
|
1822
|
+
export default Papa;
|
1823
|
+
|
1824
|
+
export {CsvToJson, CsvToJson as parse,JsonToCsv,JsonToCsv as unparse};
|