-
Notifications
You must be signed in to change notification settings - Fork 217
/
writer.rs
1396 lines (1328 loc) · 44.8 KB
/
writer.rs
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
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
use std::fs::File;
use std::io;
use std::path::Path;
use std::result;
use csv_core::{
self,
Writer as CoreWriter,
WriterBuilder as CoreWriterBuilder,
WriteResult,
};
use serde::Serialize;
use byte_record::ByteRecord;
use error::{
ErrorKind, Result, IntoInnerError,
new_error, new_into_inner_error,
};
use serializer::{serialize, serialize_header};
use {QuoteStyle, Terminator};
/// Builds a CSV writer with various configuration knobs.
///
/// This builder can be used to tweak the field delimiter, record terminator
/// and more. Once a CSV `Writer` is built, its configuration cannot be
/// changed.
#[derive(Debug)]
pub struct WriterBuilder {
builder: CoreWriterBuilder,
capacity: usize,
flexible: bool,
has_headers: bool,
}
impl Default for WriterBuilder {
fn default() -> WriterBuilder {
WriterBuilder {
builder: CoreWriterBuilder::default(),
capacity: 8 * (1<<10),
flexible: false,
has_headers: true,
}
}
}
impl WriterBuilder {
/// Create a new builder for configuring CSV writing.
///
/// To convert a builder into a writer, call one of the methods starting
/// with `from_`.
///
/// # Example
///
/// ```
/// extern crate csv;
///
/// use std::error::Error;
/// use csv::WriterBuilder;
///
/// # fn main() { example().unwrap(); }
/// fn example() -> Result<(), Box<Error>> {
/// let mut wtr = WriterBuilder::new().from_writer(vec![]);
/// wtr.write_record(&["a", "b", "c"])?;
/// wtr.write_record(&["x", "y", "z"])?;
///
/// let data = String::from_utf8(wtr.into_inner()?)?;
/// assert_eq!(data, "a,b,c\nx,y,z\n");
/// Ok(())
/// }
/// ```
pub fn new() -> WriterBuilder {
WriterBuilder::default()
}
/// Build a CSV writer from this configuration that writes data to the
/// given file path. The file is truncated if it already exists.
///
/// If there was a problem opening the file at the given path, then this
/// returns the corresponding error.
///
/// # Example
///
/// ```no_run
/// extern crate csv;
///
/// use std::error::Error;
/// use csv::WriterBuilder;
///
/// # fn main() { example().unwrap(); }
/// fn example() -> Result<(), Box<Error>> {
/// let mut wtr = WriterBuilder::new().from_path("foo.csv")?;
/// wtr.write_record(&["a", "b", "c"])?;
/// wtr.write_record(&["x", "y", "z"])?;
/// wtr.flush()?;
/// Ok(())
/// }
/// ```
pub fn from_path<P: AsRef<Path>>(&self, path: P) -> Result<Writer<File>> {
Ok(Writer::new(self, File::create(path)?))
}
/// Build a CSV writer from this configuration that writes data to `wtr`.
///
/// Note that the CSV writer is buffered automatically, so you should not
/// wrap `wtr` in a buffered writer like `io::BufWriter`.
///
/// # Example
///
/// ```
/// extern crate csv;
///
/// use std::error::Error;
/// use csv::WriterBuilder;
///
/// # fn main() { example().unwrap(); }
/// fn example() -> Result<(), Box<Error>> {
/// let mut wtr = WriterBuilder::new().from_writer(vec![]);
/// wtr.write_record(&["a", "b", "c"])?;
/// wtr.write_record(&["x", "y", "z"])?;
///
/// let data = String::from_utf8(wtr.into_inner()?)?;
/// assert_eq!(data, "a,b,c\nx,y,z\n");
/// Ok(())
/// }
/// ```
pub fn from_writer<W: io::Write>(&self, wtr: W) -> Writer<W> {
Writer::new(self, wtr)
}
/// The field delimiter to use when writing CSV.
///
/// The default is `b','`.
///
/// # Example
///
/// ```
/// extern crate csv;
///
/// use std::error::Error;
/// use csv::WriterBuilder;
///
/// # fn main() { example().unwrap(); }
/// fn example() -> Result<(), Box<Error>> {
/// let mut wtr = WriterBuilder::new()
/// .delimiter(b';')
/// .from_writer(vec![]);
/// wtr.write_record(&["a", "b", "c"])?;
/// wtr.write_record(&["x", "y", "z"])?;
///
/// let data = String::from_utf8(wtr.into_inner()?)?;
/// assert_eq!(data, "a;b;c\nx;y;z\n");
/// Ok(())
/// }
/// ```
pub fn delimiter(&mut self, delimiter: u8) -> &mut WriterBuilder {
self.builder.delimiter(delimiter);
self
}
/// Whether to write a header row before writing any other row.
///
/// When this is enabled and the `serialize` method is used to write data
/// with something that contains field names (i.e., a struct), then a
/// header row is written containing the field names before any other row
/// is written.
///
/// This option has no effect when using other methods to write rows. That
/// is, if you don't use `serialize`, then you must write your header row
/// explicitly if you want a header row.
///
/// This is enabled by default.
///
/// # Example: with headers
///
/// This shows how the header will be automatically written from the field
/// names of a struct.
///
/// ```
/// extern crate csv;
/// #[macro_use]
/// extern crate serde_derive;
///
/// use std::error::Error;
/// use csv::WriterBuilder;
///
/// #[derive(Serialize)]
/// struct Row<'a> {
/// city: &'a str,
/// country: &'a str,
/// // Serde allows us to name our headers exactly,
/// // even if they don't match our struct field names.
/// #[serde(rename = "popcount")]
/// population: u64,
/// }
///
/// # fn main() { example().unwrap(); }
/// fn example() -> Result<(), Box<Error>> {
/// let mut wtr = WriterBuilder::new().from_writer(vec![]);
/// wtr.serialize(Row {
/// city: "Boston",
/// country: "United States",
/// population: 4628910,
/// })?;
/// wtr.serialize(Row {
/// city: "Concord",
/// country: "United States",
/// population: 42695,
/// })?;
///
/// let data = String::from_utf8(wtr.into_inner()?)?;
/// assert_eq!(data, "\
///city,country,popcount
///Boston,United States,4628910
///Concord,United States,42695
///");
/// Ok(())
/// }
/// ```
///
/// # Example: without headers
///
/// This shows that serializing things that aren't structs (in this case,
/// a tuple struct) won't result in a header row being written. This means
/// you usually don't need to set `has_headers(false)` unless you
/// explicitly want to both write custom headers and serialize structs.
///
/// ```
/// extern crate csv;
///
/// use std::error::Error;
/// use csv::WriterBuilder;
///
/// # fn main() { example().unwrap(); }
/// fn example() -> Result<(), Box<Error>> {
/// let mut wtr = WriterBuilder::new().from_writer(vec![]);
/// wtr.serialize(("Boston", "United States", 4628910))?;
/// wtr.serialize(("Concord", "United States", 42695))?;
///
/// let data = String::from_utf8(wtr.into_inner()?)?;
/// assert_eq!(data, "\
///Boston,United States,4628910
///Concord,United States,42695
///");
/// Ok(())
/// }
/// ```
pub fn has_headers(&mut self, yes: bool) -> &mut WriterBuilder {
self.has_headers = yes;
self
}
/// Whether the number of fields in records is allowed to change or not.
///
/// When disabled (which is the default), writing CSV data will return an
/// error if a record is written with a number of fields different from the
/// number of fields written in a previous record.
///
/// When enabled, this error checking is turned off.
///
/// # Example: writing flexible records
///
/// ```
/// extern crate csv;
///
/// use std::error::Error;
/// use csv::WriterBuilder;
///
/// # fn main() { example().unwrap(); }
/// fn example() -> Result<(), Box<Error>> {
/// let mut wtr = WriterBuilder::new()
/// .flexible(true)
/// .from_writer(vec![]);
/// wtr.write_record(&["a", "b"])?;
/// wtr.write_record(&["x", "y", "z"])?;
///
/// let data = String::from_utf8(wtr.into_inner()?)?;
/// assert_eq!(data, "a,b\nx,y,z\n");
/// Ok(())
/// }
/// ```
///
/// # Example: error when `flexible` is disabled
///
/// ```
/// extern crate csv;
///
/// use std::error::Error;
/// use csv::WriterBuilder;
///
/// # fn main() { example().unwrap(); }
/// fn example() -> Result<(), Box<Error>> {
/// let mut wtr = WriterBuilder::new()
/// .flexible(false)
/// .from_writer(vec![]);
/// wtr.write_record(&["a", "b"])?;
/// let err = wtr.write_record(&["x", "y", "z"]).unwrap_err();
/// match *err.kind() {
/// csv::ErrorKind::UnequalLengths { expected_len, len, .. } => {
/// assert_eq!(expected_len, 2);
/// assert_eq!(len, 3);
/// }
/// ref wrong => {
/// panic!("expected UnequalLengths but got {:?}", wrong);
/// }
/// }
/// Ok(())
/// }
/// ```
pub fn flexible(&mut self, yes: bool) -> &mut WriterBuilder {
self.flexible = yes;
self
}
/// The record terminator to use when writing CSV.
///
/// A record terminator can be any single byte. The default is `\n`.
///
/// Note that RFC 4180 specifies that record terminators should be `\r\n`.
/// To use `\r\n`, use the special `Terminator::CRLF` value.
///
/// # Example: CRLF
///
/// This shows how to use RFC 4180 compliant record terminators.
///
/// ```
/// extern crate csv;
///
/// use std::error::Error;
/// use csv::{Terminator, WriterBuilder};
///
/// # fn main() { example().unwrap(); }
/// fn example() -> Result<(), Box<Error>> {
/// let mut wtr = WriterBuilder::new()
/// .terminator(Terminator::CRLF)
/// .from_writer(vec![]);
/// wtr.write_record(&["a", "b", "c"])?;
/// wtr.write_record(&["x", "y", "z"])?;
///
/// let data = String::from_utf8(wtr.into_inner()?)?;
/// assert_eq!(data, "a,b,c\r\nx,y,z\r\n");
/// Ok(())
/// }
/// ```
pub fn terminator(
&mut self,
term: Terminator,
) -> &mut WriterBuilder {
self.builder.terminator(term.to_core());
self
}
/// The quoting style to use when writing CSV.
///
/// By default, this is set to `QuoteStyle::Necessary`, which will only
/// use quotes when they are necessary to preserve the integrity of data.
///
/// Note that unless the quote style is set to `Never`, an empty field is
/// quoted if it is the only field in a record.
///
/// # Example: non-numeric quoting
///
/// This shows how to quote non-numeric fields only.
///
/// ```
/// extern crate csv;
///
/// use std::error::Error;
/// use csv::{QuoteStyle, WriterBuilder};
///
/// # fn main() { example().unwrap(); }
/// fn example() -> Result<(), Box<Error>> {
/// let mut wtr = WriterBuilder::new()
/// .quote_style(QuoteStyle::NonNumeric)
/// .from_writer(vec![]);
/// wtr.write_record(&["a", "5", "c"])?;
/// wtr.write_record(&["3.14", "y", "z"])?;
///
/// let data = String::from_utf8(wtr.into_inner()?)?;
/// assert_eq!(data, "\"a\",5,\"c\"\n3.14,\"y\",\"z\"\n");
/// Ok(())
/// }
/// ```
///
/// # Example: never quote
///
/// This shows how the CSV writer can be made to never write quotes, even
/// if it sacrifices the integrity of the data.
///
/// ```
/// extern crate csv;
///
/// use std::error::Error;
/// use csv::{QuoteStyle, WriterBuilder};
///
/// # fn main() { example().unwrap(); }
/// fn example() -> Result<(), Box<Error>> {
/// let mut wtr = WriterBuilder::new()
/// .quote_style(QuoteStyle::Never)
/// .from_writer(vec![]);
/// wtr.write_record(&["a", "foo\nbar", "c"])?;
/// wtr.write_record(&["g\"h\"i", "y", "z"])?;
///
/// let data = String::from_utf8(wtr.into_inner()?)?;
/// assert_eq!(data, "a,foo\nbar,c\ng\"h\"i,y,z\n");
/// Ok(())
/// }
/// ```
pub fn quote_style(&mut self, style: QuoteStyle) -> &mut WriterBuilder {
self.builder.quote_style(style.to_core());
self
}
/// The quote character to use when writing CSV.
///
/// The default is `b'"'`.
///
/// # Example
///
/// ```
/// extern crate csv;
///
/// use std::error::Error;
/// use csv::WriterBuilder;
///
/// # fn main() { example().unwrap(); }
/// fn example() -> Result<(), Box<Error>> {
/// let mut wtr = WriterBuilder::new()
/// .quote(b'\'')
/// .from_writer(vec![]);
/// wtr.write_record(&["a", "foo\nbar", "c"])?;
/// wtr.write_record(&["g'h'i", "y\"y\"y", "z"])?;
///
/// let data = String::from_utf8(wtr.into_inner()?)?;
/// assert_eq!(data, "a,'foo\nbar',c\n'g''h''i',y\"y\"y,z\n");
/// Ok(())
/// }
/// ```
pub fn quote(&mut self, quote: u8) -> &mut WriterBuilder {
self.builder.quote(quote);
self
}
/// Enable double quote escapes.
///
/// This is enabled by default, but it may be disabled. When disabled,
/// quotes in field data are escaped instead of doubled.
///
/// # Example
///
/// ```
/// extern crate csv;
///
/// use std::error::Error;
/// use csv::WriterBuilder;
///
/// # fn main() { example().unwrap(); }
/// fn example() -> Result<(), Box<Error>> {
/// let mut wtr = WriterBuilder::new()
/// .double_quote(false)
/// .from_writer(vec![]);
/// wtr.write_record(&["a", "foo\"bar", "c"])?;
/// wtr.write_record(&["x", "y", "z"])?;
///
/// let data = String::from_utf8(wtr.into_inner()?)?;
/// assert_eq!(data, "a,\"foo\\\"bar\",c\nx,y,z\n");
/// Ok(())
/// }
/// ```
pub fn double_quote(&mut self, yes: bool) -> &mut WriterBuilder {
self.builder.double_quote(yes);
self
}
/// The escape character to use when writing CSV.
///
/// In some variants of CSV, quotes are escaped using a special escape
/// character like `\` (instead of escaping quotes by doubling them).
///
/// By default, writing these idiosyncratic escapes is disabled, and is
/// only used when `double_quote` is disabled.
///
/// # Example
///
/// ```
/// extern crate csv;
///
/// use std::error::Error;
/// use csv::WriterBuilder;
///
/// # fn main() { example().unwrap(); }
/// fn example() -> Result<(), Box<Error>> {
/// let mut wtr = WriterBuilder::new()
/// .double_quote(false)
/// .escape(b'$')
/// .from_writer(vec![]);
/// wtr.write_record(&["a", "foo\"bar", "c"])?;
/// wtr.write_record(&["x", "y", "z"])?;
///
/// let data = String::from_utf8(wtr.into_inner()?)?;
/// assert_eq!(data, "a,\"foo$\"bar\",c\nx,y,z\n");
/// Ok(())
/// }
/// ```
pub fn escape(&mut self, escape: u8) -> &mut WriterBuilder {
self.builder.escape(escape);
self
}
/// Set the capacity (in bytes) of the internal buffer used in the CSV
/// writer. This defaults to a reasonable setting.
pub fn buffer_capacity(&mut self, capacity: usize) -> &mut WriterBuilder {
self.capacity = capacity;
self
}
}
/// A already configured CSV writer.
///
/// A CSV writer takes as input Rust values and writes those values in a valid
/// CSV format as output.
///
/// While CSV writing is considerably easier than parsing CSV, a proper writer
/// will do a number of things for you:
///
/// 1. Quote fields when necessary.
/// 2. Check that all records have the same number of fields.
/// 3. Write records with a single empty field correctly.
/// 4. Automatically serialize normal Rust types to CSV records. When that
/// type is a struct, a header row is automatically written corresponding
/// to the fields of that struct.
/// 5. Use buffering intelligently and otherwise avoid allocation. (This means
/// that callers should not do their own buffering.)
///
/// All of the above can be configured using a
/// [`WriterBuilder`](struct.WriterBuilder.html).
/// However, a `Writer` has a couple of convenience constructors (`from_path`
/// and `from_writer`) that use the default configuration.
///
/// Note that the default configuration of a `Writer` uses `\n` for record
/// terminators instead of `\r\n` as specified by RFC 4180. Use the
/// `terminator` method on `WriterBuilder` to set the terminator to `\r\n` if
/// it's desired.
#[derive(Debug)]
pub struct Writer<W: io::Write> {
core: CoreWriter,
wtr: Option<W>,
buf: Buffer,
state: WriterState,
}
#[derive(Debug)]
struct WriterState {
/// Whether the Serde serializer should attempt to write a header row.
header: HeaderState,
/// Whether inconsistent record lengths are allowed.
flexible: bool,
/// The number of fields writtein in the first record. This is compared
/// with `fields_written` on all subsequent records to check for
/// inconsistent record lengths.
first_field_count: Option<u64>,
/// The number of fields written in this record. This is used to report
/// errors for inconsistent record lengths if `flexible` is disabled.
fields_written: u64,
/// This is set immediately before flushing the buffer and then unset
/// immediately after flushing the buffer. This avoids flushing the buffer
/// twice if the inner writer panics.
panicked: bool,
}
/// HeaderState encodes a small state machine for handling header writes.
#[derive(Debug)]
enum HeaderState {
/// Indicates that we should attempt to write a header.
Write,
/// Indicates that writing a header was attempt, and a header was written.
DidWrite,
/// Indicates that writing a header was attempted, but no headers were
/// written or the attempt failed.
DidNotWrite,
/// This state is used when headers are disabled. It cannot transition
/// to any other state.
None,
}
/// A simple internal buffer for buffering writes.
///
/// We need this because the `csv_core` APIs want to write into a `&mut [u8]`,
/// which is not available with the `std::io::BufWriter` API.
#[derive(Debug)]
struct Buffer {
/// The contents of the buffer.
buf: Vec<u8>,
/// The number of bytes written to the buffer.
len: usize,
}
impl<W: io::Write> Drop for Writer<W> {
fn drop(&mut self) {
if self.wtr.is_some() && !self.state.panicked {
let _ = self.flush();
}
}
}
impl Writer<File> {
/// Build a CSV writer with a default configuration that writes data to the
/// given file path. The file is truncated if it already exists.
///
/// If there was a problem opening the file at the given path, then this
/// returns the corresponding error.
///
/// # Example
///
/// ```no_run
/// extern crate csv;
///
/// use std::error::Error;
/// use csv::Writer;
///
/// # fn main() { example().unwrap(); }
/// fn example() -> Result<(), Box<Error>> {
/// let mut wtr = Writer::from_path("foo.csv")?;
/// wtr.write_record(&["a", "b", "c"])?;
/// wtr.write_record(&["x", "y", "z"])?;
/// wtr.flush()?;
/// Ok(())
/// }
/// ```
pub fn from_path<P: AsRef<Path>>(path: P) -> Result<Writer<File>> {
WriterBuilder::new().from_path(path)
}
}
impl<W: io::Write> Writer<W> {
fn new(builder: &WriterBuilder, wtr: W) -> Writer<W> {
let header_state =
if builder.has_headers {
HeaderState::Write
} else {
HeaderState::None
};
Writer {
core: builder.builder.build(),
wtr: Some(wtr),
buf: Buffer {
buf: vec![0; builder.capacity],
len: 0,
},
state: WriterState {
header: header_state,
flexible: builder.flexible,
first_field_count: None,
fields_written: 0,
panicked: false,
},
}
}
/// Build a CSV writer with a default configuration that writes data to
/// `wtr`.
///
/// Note that the CSV writer is buffered automatically, so you should not
/// wrap `wtr` in a buffered writer like `io::BufWriter`.
///
/// # Example
///
/// ```
/// extern crate csv;
///
/// use std::error::Error;
/// use csv::Writer;
///
/// # fn main() { example().unwrap(); }
/// fn example() -> Result<(), Box<Error>> {
/// let mut wtr = Writer::from_writer(vec![]);
/// wtr.write_record(&["a", "b", "c"])?;
/// wtr.write_record(&["x", "y", "z"])?;
///
/// let data = String::from_utf8(wtr.into_inner()?)?;
/// assert_eq!(data, "a,b,c\nx,y,z\n");
/// Ok(())
/// }
/// ```
pub fn from_writer(wtr: W) -> Writer<W> {
WriterBuilder::new().from_writer(wtr)
}
/// Serialize a single record using Serde.
///
/// # Example
///
/// This shows how to serialize normal Rust structs as CSV records. The
/// fields of the struct are used to write a header row automatically.
/// (Writing the header row automatically can be disabled by building the
/// CSV writer with a [`WriterBuilder`](struct.WriterBuilder.html) and
/// calling the `has_headers` method.)
///
/// ```
/// extern crate csv;
/// #[macro_use]
/// extern crate serde_derive;
///
/// use std::error::Error;
/// use csv::Writer;
///
/// #[derive(Serialize)]
/// struct Row<'a> {
/// city: &'a str,
/// country: &'a str,
/// // Serde allows us to name our headers exactly,
/// // even if they don't match our struct field names.
/// #[serde(rename = "popcount")]
/// population: u64,
/// }
///
/// # fn main() { example().unwrap(); }
/// fn example() -> Result<(), Box<Error>> {
/// let mut wtr = Writer::from_writer(vec![]);
/// wtr.serialize(Row {
/// city: "Boston",
/// country: "United States",
/// population: 4628910,
/// })?;
/// wtr.serialize(Row {
/// city: "Concord",
/// country: "United States",
/// population: 42695,
/// })?;
///
/// let data = String::from_utf8(wtr.into_inner()?)?;
/// assert_eq!(data, "\
/// city,country,popcount
/// Boston,United States,4628910
/// Concord,United States,42695
/// ");
/// Ok(())
/// }
/// ```
///
/// # Rules
///
/// The behavior of `serialize` is fairly simple:
///
/// 1. Nested containers (tuples, `Vec`s, structs, etc.) are always
/// flattened (depth-first order).
///
/// 2. If `has_headers` is `true` and the type contains field names, then
/// a header row is automatically generated.
///
/// However, some container types cannot be serialized, and if
/// `has_headers` is `true`, there are some additional restrictions on the
/// types that can be serialized. See below for details.
///
/// For the purpose of this section, Rust types can be divided into three
/// categories: scalars, non-struct containers, and structs.
///
/// ## Scalars
///
/// Single values with no field names are written like the following. Note
/// that some of the outputs may be quoted, according to the selected
/// quoting style.
///
/// | Name | Example Type | Example Value | Output |
/// | ---- | ---- | ---- | ---- |
/// | boolean | `bool` | `true` | `true` |
/// | integers | `i8`, `i16`, `i32`, `i64`, `u8`, `u16`, `u32`, `u64` | `5` | `5` |
/// | floats | `f32`, `f64` | `3.14` | `3.14` |
/// | character | `char` | `'☃'` | `☃` |
/// | string | `&str` | `"hi"` | `hi` |
/// | bytes | `&[u8]` | `b"hi"[..]` | `hi` |
/// | option | `Option` | `None` | *empty* |
/// | option | | `Some(5)` | `5` |
/// | unit | `()` | `()` | *empty* |
/// | unit struct | `struct Foo;` | `Foo` | `Foo` |
/// | unit enum variant | `enum E { A, B }` | `E::A` | `A` |
/// | newtype struct | `struct Foo(u8);` | `Foo(5)` | `5` |
/// | newtype enum variant | `enum E { A(u8) }` | `E::A(5)` | `5` |
///
/// Note that this table includes simple structs and enums. For example, to
/// serialize a field from either an integer or a float type, one can do
/// this:
///
/// ```
/// extern crate csv;
/// #[macro_use]
/// extern crate serde_derive;
///
/// use std::error::Error;
/// use csv::Writer;
///
/// #[derive(Serialize)]
/// struct Row {
/// label: String,
/// value: Value,
/// }
///
/// #[derive(Serialize)]
/// enum Value {
/// Integer(i64),
/// Float(f64),
/// }
///
/// # fn main() { example().unwrap(); }
/// fn example() -> Result<(), Box<Error>> {
/// let mut wtr = Writer::from_writer(vec![]);
/// wtr.serialize(Row {
/// label: "foo".to_string(),
/// value: Value::Integer(3),
/// })?;
/// wtr.serialize(Row {
/// label: "bar".to_string(),
/// value: Value::Float(3.14),
/// })?;
///
/// let data = String::from_utf8(wtr.into_inner()?)?;
/// assert_eq!(data, "\
/// label,value
/// foo,3
/// bar,3.14
/// ");
/// Ok(())
/// }
/// ```
///
/// ## Non-Struct Containers
///
/// Nested containers are flattened to their scalar components, with the
/// exeption of a few types that are not allowed:
///
/// | Name | Example Type | Example Value | Output |
/// | ---- | ---- | ---- | ---- |
/// | sequence | `Vec<u8>` | `vec![1, 2, 3]` | `1,2,3` |
/// | tuple | `(u8, bool)` | `(5, true)` | `5,true` |
/// | tuple struct | `Foo(u8, bool)` | `Foo(5, true)` | `5,true` |
/// | tuple enum variant | `enum E { A(u8, bool) }` | `E::A(5, true)` | *error* |
/// | struct enum variant | `enum E { V { a: u8, b: bool } }` | `E::V { a: 5, b: true }` | *error* |
/// | map | `BTreeMap<K, V>` | `BTreeMap::new()` | *error* |
///
/// ## Structs
///
/// Like the other containers, structs are flattened to their scalar
/// components:
///
/// | Name | Example Type | Example Value | Output |
/// | ---- | ---- | ---- | ---- |
/// | struct | `struct Foo { a: u8, b: bool }` | `Foo { a: 5, b: true }` | `5,true` |
///
/// If `has_headers` is `false`, then there are no additional restrictions;
/// types can be nested arbitrarily. For example:
///
/// ```
/// extern crate csv;
/// #[macro_use]
/// extern crate serde_derive;
///
/// use std::error::Error;
/// use csv::WriterBuilder;
///
/// #[derive(Serialize)]
/// struct Row {
/// label: String,
/// values: Vec<f64>,
/// }
///
/// # fn main() { example().unwrap(); }
/// fn example() -> Result<(), Box<Error>> {
/// let mut wtr = WriterBuilder::new()
/// .has_headers(false)
/// .from_writer(vec![]);
/// wtr.serialize(Row {
/// label: "foo".to_string(),
/// values: vec![1.1234, 2.5678, 3.14],
/// })?;
///
/// let data = String::from_utf8(wtr.into_inner()?)?;
/// assert_eq!(data, "\
/// foo,1.1234,2.5678,3.14
/// ");
/// Ok(())
/// }
/// ```
///
/// However, if `has_headers` were enabled in the above example, then
/// serialization would return an error. Speficially, when `has_headers` is
/// `true`, there are two restrictions:
///
/// 1. Named field values in structs must be scalars.
///
/// 2. All scalars must be named field values in structs.
///
/// Other than these two restrictions, types can be nested arbitrarily.
/// Here are a few examples:
///
/// | Value | Header | Record |
/// | ---- | ---- | ---- |
/// | `(Foo { x: 5, y: 6 }, Bar { z: true })` | `x,y,z` | `5,6,true` |
/// | `vec![Foo { x: 5, y: 6 }, Foo { x: 7, y: 8 }]` | `x,y,x,y` | `5,6,7,8` |
/// | `(Foo { x: 5, y: 6 }, vec![Bar { z: Baz(true) }])` | `x,y,z` | `5,6,true` |
/// | `Foo { x: 5, y: (6, 7) }` | *error: restriction 1* | `5,6,7` |
/// | `(5, Foo { x: 6, y: 7 }` | *error: restriction 2* | `5,6,7` |
/// | `(Foo { x: 5, y: 6 }, true)` | *error: restriction 2* | `5,6,true` |
pub fn serialize<S: Serialize>(&mut self, record: S) -> Result<()> {
if let HeaderState::Write = self.state.header {
let wrote_header = serialize_header(self, &record)?;
if wrote_header {
self.write_terminator()?;
self.state.header = HeaderState::DidWrite;
} else {
self.state.header = HeaderState::DidNotWrite;
};
}
serialize(self, &record)?;
self.write_terminator()?;
Ok(())
}
/// Write a single record.
///
/// This method accepts something that can be turned into an iterator that
/// yields elements that can be represented by a `&[u8]`.
///
/// This may be called with an empty iterator, which will cause a record
/// terminator to be written. If no fields had been written, then a single
/// empty field is written before the terminator.
///
/// # Example
///
/// ```
/// extern crate csv;
///
/// use std::error::Error;
/// use csv::Writer;
///
/// # fn main() { example().unwrap(); }
/// fn example() -> Result<(), Box<Error>> {
/// let mut wtr = Writer::from_writer(vec![]);
/// wtr.write_record(&["a", "b", "c"])?;
/// wtr.write_record(&["x", "y", "z"])?;
///
/// let data = String::from_utf8(wtr.into_inner()?)?;
/// assert_eq!(data, "a,b,c\nx,y,z\n");
/// Ok(())
/// }
/// ```
pub fn write_record<I, T>(&mut self, record: I) -> Result<()>
where I: IntoIterator<Item=T>, T: AsRef<[u8]>
{
for field in record.into_iter() {
self.write_field_impl(field)?;
}
self.write_terminator()
}
/// Write a single `ByteRecord`.
///
/// This method accepts a borrowed `ByteRecord` and writes its contents
/// to the underlying writer.
///
/// This is similar to `write_record` except that it specifically requires
/// a `ByteRecord`. This permits the writer to possibly write the record
/// more quickly than the more generic `write_record`.
///
/// This may be called with an empty record, which will cause a record
/// terminator to be written. If no fields had been written, then a single
/// empty field is written before the terminator.
///
/// # Example
///
/// ```
/// extern crate csv;
///
/// use std::error::Error;
/// use csv::{ByteRecord, Writer};
///
/// # fn main() { example().unwrap(); }
/// fn example() -> Result<(), Box<Error>> {
/// let mut wtr = Writer::from_writer(vec![]);
/// wtr.write_byte_record(&ByteRecord::from(&["a", "b", "c"][..]))?;
/// wtr.write_byte_record(&ByteRecord::from(&["x", "y", "z"][..]))?;
///
/// let data = String::from_utf8(wtr.into_inner()?)?;
/// assert_eq!(data, "a,b,c\nx,y,z\n");
/// Ok(())
/// }
/// ```
#[inline(never)]
pub fn write_byte_record(&mut self, record: &ByteRecord) -> Result<()> {
if record.as_slice().is_empty() {
return self.write_record(record);
}
// The idea here is to find a fast path for shuffling our record into
// our buffer as quickly as possible. We do this because the underlying
// "core" CSV writer does a lot of book-keeping to maintain its state
// oriented API.
//
// The fast path occurs when we know our record will fit in whatever
// space we have left in our buffer. We can actually quickly compute
// the upper bound on the space required:
let upper_bound =
// The data itself plus the worst case: every byte is a quote.