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 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368
use futures::io;
use crate::AsyncReaderBuilder;
use crate::byte_record::{ByteRecord, Position};
use crate::error::Result;
use crate::string_record::StringRecord;
use super::{
AsyncReaderImpl,
StringRecordsStream, StringRecordsIntoStream,
ByteRecordsStream, ByteRecordsIntoStream,
};
impl AsyncReaderBuilder {
/// Build a CSV reader from this configuration that reads data from `rdr`.
///
/// Note that the CSV reader is buffered automatically, so you should not
/// wrap `rdr` in a buffered reader.
///
/// # Example
///
/// ```
/// use std::error::Error;
/// use futures::stream::StreamExt;
/// use csv_async::AsyncReaderBuilder;
///
/// # fn main() { async_std::task::block_on(async {example().await.unwrap()}); }
/// async fn example() -> Result<(), Box<dyn Error>> {
/// let data = "\
/// city,country,pop
/// Boston,United States,4628910
/// Concord,United States,42695
/// ";
/// let mut rdr = AsyncReaderBuilder::new().create_reader(data.as_bytes());
/// let mut records = rdr.into_records();
/// while let Some(record) = records.next().await {
/// println!("{:?}", record?);
/// }
/// Ok(())
/// }
/// ```
pub fn create_reader<R: io::AsyncRead + Unpin + Send>(&self, rdr: R) -> AsyncReader<R> {
AsyncReader::new(self, rdr)
}
}
/// A already configured CSV reader.
///
/// A CSV reader takes as input CSV data and transforms that into standard Rust
/// values. The reader reads CSV data is as a sequence of records,
/// where a record is a sequence of fields and each field is a string.
///
/// # Configuration
///
/// A CSV reader has convenient constructor method `from_reader`.
/// However, if you want to configure the CSV reader to use
/// a different delimiter or quote character (among many other things), then
/// you should use a [`AsyncReaderBuilder`](struct.AsyncReaderBuilder.html) to construct
/// a `AsyncReader`. For example, to change the field delimiter:
///
/// ```
/// use std::error::Error;
/// use futures::stream::StreamExt;
/// use csv_async::AsyncReaderBuilder;
///
/// # fn main() { async_std::task::block_on(async {example().await.unwrap()}); }
/// async fn example() -> Result<(), Box<dyn Error>> {
/// let data = "\
/// city;country;pop
/// Boston;United States;4628910
/// ";
/// let mut rdr = AsyncReaderBuilder::new()
/// .delimiter(b';')
/// .create_reader(data.as_bytes());
///
/// let mut records = rdr.records();
/// assert_eq!(records.next().await.unwrap()?, vec!["Boston", "United States", "4628910"]);
/// Ok(())
/// }
/// ```
///
/// # Error handling
///
/// In general, CSV *parsing* does not ever return an error. That is, there is
/// no such thing as malformed CSV data. Instead, this reader will prioritize
/// finding a parse over rejecting CSV data that it does not understand. This
/// choice was inspired by other popular CSV parsers, but also because it is
/// pragmatic. CSV data varies wildly, so even if the CSV data is malformed,
/// it might still be possible to work with the data. In the land of CSV, there
/// is no "right" or "wrong," only "right" and "less right."
///
/// With that said, a number of errors can occur while reading CSV data:
///
/// * By default, all records in CSV data must have the same number of fields.
/// If a record is found with a different number of fields than a prior
/// record, then an error is returned. This behavior can be disabled by
/// enabling flexible parsing via the `flexible` method on
/// [`AsyncReaderBuilder`](struct.AsyncReaderBuilder.html).
/// * When reading CSV data from a resource (like a file), it is possible for
/// reading from the underlying resource to fail. This will return an error.
/// For subsequent calls to the reader after encountering a such error
/// (unless `seek` is used), it will behave as if end of file had been
/// reached, in order to avoid running into infinite loops when still
/// attempting to read the next record when one has errored.
/// * When reading CSV data into `String` or `&str` fields (e.g., via a
/// [`StringRecord`](struct.StringRecord.html)), UTF-8 is strictly
/// enforced. If CSV data is invalid UTF-8, then an error is returned. If
/// you want to read invalid UTF-8, then you should use the byte oriented
/// APIs such as [`ByteRecord`](struct.ByteRecord.html). If you need explicit
/// support for another encoding entirely, then you'll need to use another
/// crate to transcode your CSV data to UTF-8 before parsing it.
/// * When using Serde to deserialize CSV data into Rust types, it is possible
/// for a number of additional errors to occur. For example, deserializing
/// a field `xyz` into an `i32` field will result in an error.
///
/// For more details on the precise semantics of errors, see the
/// [`Error`](enum.Error.html) type.
#[derive(Debug)]
pub struct AsyncReader<R>(AsyncReaderImpl<R>);
impl<'r, R> AsyncReader<R>
where
R: io::AsyncRead + Unpin + Send + 'r,
{
/// Create a new CSV reader given a builder and a source of underlying
/// bytes.
fn new(builder: &AsyncReaderBuilder, rdr: R) -> AsyncReader<R> {
AsyncReader(AsyncReaderImpl::new(builder, rdr))
}
/// Create a new CSV parser with a default configuration for the given
/// reader.
///
/// To customize CSV parsing, use a `ReaderBuilder`.
///
/// # Example
///
/// ```
/// use std::error::Error;
/// use futures::stream::StreamExt;
/// use csv_async::AsyncReader;
///
/// # fn main() { async_std::task::block_on(async {example().await.unwrap()}); }
/// async fn example() -> Result<(), Box<dyn Error>> {
/// let data = "\
/// city,country,pop
/// Boston,United States,4628910
/// Concord,United States,42695
/// ";
/// let mut rdr = AsyncReader::from_reader(data.as_bytes());
/// let mut records = rdr.into_records();
/// while let Some(record) = records.next().await {
/// println!("{:?}", record?);
/// }
/// Ok(())
/// }
/// ```
#[inline]
pub fn from_reader(rdr: R) -> AsyncReader<R> {
AsyncReaderBuilder::new().create_reader(rdr)
}
/// Returns a borrowed iterator over all records as strings.
///
/// Each item yielded by this iterator is a `Result<StringRecord, Error>`.
/// Therefore, in order to access the record, callers must handle the
/// possibility of error (typically with `try!` or `?`).
///
/// If `has_headers` was enabled via a `ReaderBuilder` (which is the
/// default), then this does not include the first record.
///
/// # Example
///
/// ```
/// use std::error::Error;
/// use futures::stream::StreamExt;
/// use csv_async::AsyncReader;
///
/// # fn main() { async_std::task::block_on(async {example().await.unwrap()}); }
/// async fn example() -> Result<(), Box<dyn Error>> {
/// let data = "\
/// city,country,pop
/// Boston,United States,4628910
/// ";
/// let mut rdr = AsyncReader::from_reader(data.as_bytes());
/// let mut records = rdr.records();
/// while let Some(record) = records.next().await {
/// println!("{:?}", record?);
/// }
/// Ok(())
/// }
/// ```
#[inline]
pub fn records(&mut self) -> StringRecordsStream<R> {
StringRecordsStream::new(&mut self.0)
}
/// Returns an owned iterator over all records as strings.
///
/// Each item yielded by this iterator is a `Result<StringRecord, Error>`.
/// Therefore, in order to access the record, callers must handle the
/// possibility of error (typically with `try!` or `?`).
///
/// This is mostly useful when you want to return a CSV iterator or store
/// it somewhere.
///
/// If `has_headers` was enabled via a `ReaderBuilder` (which is the
/// default), then this does not include the first record.
///
/// # Example
///
/// ```
/// use std::error::Error;
/// use futures::stream::StreamExt;
/// use csv_async::AsyncReader;
///
/// # fn main() { async_std::task::block_on(async {example().await.unwrap()}); }
/// async fn example() -> Result<(), Box<dyn Error>> {
/// let data = "\
/// city,country,pop
/// Boston,United States,4628910
/// ";
/// let rdr = AsyncReader::from_reader(data.as_bytes());
/// let mut records = rdr.into_records();
/// while let Some(record) = records.next().await {
/// println!("{:?}", record?);
/// }
/// Ok(())
/// }
/// ```
#[inline]
pub fn into_records(self) -> StringRecordsIntoStream<'r, R> {
StringRecordsIntoStream::new(self.0)
}
/// Returns a borrowed iterator over all records as raw bytes.
///
/// Each item yielded by this iterator is a `Result<ByteRecord, Error>`.
/// Therefore, in order to access the record, callers must handle the
/// possibility of error (typically with `try!` or `?`).
///
/// If `has_headers` was enabled via a `ReaderBuilder` (which is the
/// default), then this does not include the first record.
///
/// # Example
///
/// ```
/// use std::error::Error;
/// use futures::stream::StreamExt;
/// use csv_async::AsyncReader;
///
/// # fn main() { async_std::task::block_on(async {example().await.unwrap()}); }
/// async fn example() -> Result<(), Box<dyn Error>> {
/// let data = "\
/// city,country,pop
/// Boston,United States,4628910
/// ";
/// let mut rdr = AsyncReader::from_reader(data.as_bytes());
/// let mut iter = rdr.byte_records();
/// assert_eq!(iter.next().await.unwrap()?, vec!["Boston", "United States", "4628910"]);
/// assert!(iter.next().await.is_none());
/// Ok(())
/// }
/// ```
#[inline]
pub fn byte_records(&mut self) -> ByteRecordsStream<R> {
ByteRecordsStream::new(&mut self.0)
}
/// Returns an owned iterator over all records as raw bytes.
///
/// Each item yielded by this iterator is a `Result<ByteRecord, Error>`.
/// Therefore, in order to access the record, callers must handle the
/// possibility of error (typically with `try!` or `?`).
///
/// This is mostly useful when you want to return a CSV iterator or store
/// it somewhere.
///
/// If `has_headers` was enabled via a `ReaderBuilder` (which is the
/// default), then this does not include the first record.
///
/// # Example
///
/// ```
/// use std::error::Error;
/// use futures::stream::StreamExt;
/// use csv_async::AsyncReader;
///
/// # fn main() { async_std::task::block_on(async {example().await.unwrap()}); }
/// async fn example() -> Result<(), Box<dyn Error>> {
/// let data = "\
/// city,country,pop
/// Boston,United States,4628910
/// ";
/// let rdr = AsyncReader::from_reader(data.as_bytes());
/// let mut iter = rdr.into_byte_records();
/// assert_eq!(iter.next().await.unwrap()?, vec!["Boston", "United States", "4628910"]);
/// assert!(iter.next().await.is_none());
/// Ok(())
/// }
/// ```
#[inline]
pub fn into_byte_records(self) -> ByteRecordsIntoStream<'r, R> {
ByteRecordsIntoStream::new(self.0)
}
/// Returns a reference to the first row read by this parser.
///
/// If no row has been read yet, then this will force parsing of the first
/// row.
///
/// If there was a problem parsing the row or if it wasn't valid UTF-8,
/// then this returns an error.
///
/// If the underlying reader emits EOF before any data, then this returns
/// an empty record.
///
/// Note that this method may be used regardless of whether `has_headers`
/// was enabled (but it is enabled by default).
///
/// # Example
///
/// This example shows how to get the header row of CSV data. Notice that
/// the header row does not appear as a record in the iterator!
///
/// ```
/// use std::error::Error;
/// use futures::stream::StreamExt;
/// use csv_async::AsyncReader;
///
/// # fn main() { async_std::task::block_on(async {example().await.unwrap()}); }
/// async fn example() -> Result<(), Box<dyn Error>> {
/// let data = "\
/// city,country,pop
/// Boston,United States,4628910
/// ";
/// let mut rdr = AsyncReader::from_reader(data.as_bytes());
///
/// // We can read the headers before iterating.
/// {
/// // `headers` borrows from the reader, so we put this in its
/// // own scope. That way, the borrow ends before we try iterating
/// // below. Alternatively, we could clone the headers.
/// let headers = rdr.headers().await?;
/// assert_eq!(headers, vec!["city", "country", "pop"]);
/// }
///
/// {
/// let mut records = rdr.records();
/// assert_eq!(records.next().await.unwrap()?, vec!["Boston", "United States", "4628910"]);
/// assert!(records.next().await.is_none());
/// }
///
/// // We can also read the headers after iterating.
/// let headers = rdr.headers().await?;
/// assert_eq!(headers, vec!["city", "country", "pop"]);
/// Ok(())
/// }
/// ```
#[inline]
pub async fn headers(&mut self) -> Result<&StringRecord> {
self.0.headers().await
}
/// Returns a reference to the first row read by this parser as raw bytes.
///
/// If no row has been read yet, then this will force parsing of the first
/// row.
///
/// If there was a problem parsing the row then this returns an error.
///
/// If the underlying reader emits EOF before any data, then this returns
/// an empty record.
///
/// Note that this method may be used regardless of whether `has_headers`
/// was enabled (but it is enabled by default).
///
/// # Example
///
/// This example shows how to get the header row of CSV data. Notice that
/// the header row does not appear as a record in the iterator!
///
/// ```
/// use std::error::Error;
/// use futures::stream::StreamExt;
/// use csv_async::AsyncReader;
///
/// # fn main() { async_std::task::block_on(async {example().await.unwrap()}); }
/// async fn example() -> Result<(), Box<dyn Error>> {
/// let data = "\
/// city,country,pop
/// Boston,United States,4628910
/// ";
/// let mut rdr = AsyncReader::from_reader(data.as_bytes());
///
/// // We can read the headers before iterating.
/// {
/// // `headers` borrows from the reader, so we put this in its
/// // own scope. That way, the borrow ends before we try iterating
/// // below. Alternatively, we could clone the headers.
/// let headers = rdr.byte_headers().await?;
/// assert_eq!(headers, vec!["city", "country", "pop"]);
/// }
///
/// {
/// let mut records = rdr.byte_records();
/// assert_eq!(records.next().await.unwrap()?, vec!["Boston", "United States", "4628910"]);
/// assert!(records.next().await.is_none());
/// }
///
/// // We can also read the headers after iterating.
/// let headers = rdr.byte_headers().await?;
/// assert_eq!(headers, vec!["city", "country", "pop"]);
/// Ok(())
/// }
/// ```
#[inline]
pub async fn byte_headers(&mut self) -> Result<&ByteRecord> {
self.0.byte_headers().await
}
/// Set the headers of this CSV parser manually.
///
/// This overrides any other setting (including `set_byte_headers`). Any
/// automatic detection of headers is disabled. This may be called at any
/// time.
///
/// # Example
///
/// ```
/// use std::error::Error;
/// use csv_async::{AsyncReader, StringRecord};
///
/// # fn main() { async_std::task::block_on(async {example().await.unwrap()}); }
/// async fn example() -> Result<(), Box<dyn Error>> {
/// let data = "\
/// city,country,pop
/// Boston,United States,4628910
/// ";
/// let mut rdr = AsyncReader::from_reader(data.as_bytes());
///
/// assert_eq!(rdr.headers().await?, vec!["city", "country", "pop"]);
/// rdr.set_headers(StringRecord::from(vec!["a", "b", "c"]));
/// assert_eq!(rdr.headers().await?, vec!["a", "b", "c"]);
///
/// Ok(())
/// }
/// ```
#[inline]
pub fn set_headers(&mut self, headers: StringRecord) {
self.0.set_headers(headers);
}
/// Set the headers of this CSV parser manually as raw bytes.
///
/// This overrides any other setting (including `set_headers`). Any
/// automatic detection of headers is disabled. This may be called at any
/// time.
///
/// # Example
///
/// ```
/// use std::error::Error;
/// use csv_async::{AsyncReader, ByteRecord};
///
/// # fn main() { async_std::task::block_on(async {example().await.unwrap()}); }
/// async fn example() -> Result<(), Box<dyn Error>> {
/// let data = "\
/// city,country,pop
/// Boston,United States,4628910
/// ";
/// let mut rdr = AsyncReader::from_reader(data.as_bytes());
///
/// assert_eq!(rdr.byte_headers().await?, vec!["city", "country", "pop"]);
/// rdr.set_byte_headers(ByteRecord::from(vec!["a", "b", "c"]));
/// assert_eq!(rdr.byte_headers().await?, vec!["a", "b", "c"]);
///
/// Ok(())
/// }
/// ```
#[inline]
pub fn set_byte_headers(&mut self, headers: ByteRecord) {
self.0.set_byte_headers(headers);
}
/// Read a single row into the given record. Returns false when no more
/// records could be read.
///
/// If `has_headers` was enabled via a `ReaderBuilder` (which is the
/// default), then this will treat initial row as headers and read the first data record.
///
/// This method is useful when you want to read records as fast as
/// as possible. It's less ergonomic than an iterator, but it permits the
/// caller to reuse the `StringRecord` allocation, which usually results
/// in higher throughput.
///
/// Records read via this method are guaranteed to have a position set
/// on them, even if the reader is at EOF or if an error is returned.
///
/// # Example
///
/// ```
/// use std::error::Error;
/// use csv_async::{AsyncReader, StringRecord};
///
/// # fn main() { async_std::task::block_on(async {example().await.unwrap()}); }
/// async fn example() -> Result<(), Box<dyn Error>> {
/// let data = "\
/// city,country,pop
/// Boston,United States,4628910
/// ";
/// let mut rdr = AsyncReader::from_reader(data.as_bytes());
/// let mut record = StringRecord::new();
///
/// if rdr.read_record(&mut record).await? {
/// assert_eq!(record, vec!["Boston", "United States", "4628910"]);
/// Ok(())
/// } else {
/// Err(From::from("expected at least one record but got none"))
/// }
/// }
/// ```
#[inline]
pub async fn read_record(&mut self, record: &mut StringRecord) -> Result<bool> {
self.0.read_record(record).await
}
/// Read a single row into the given byte record. Returns false when no
/// more records could be read.
///
/// If `has_headers` was enabled via a `ReaderBuilder` (which is the
/// default), then this will treat initial row as headers and read the first data record.
///
/// This method is useful when you want to read records as fast as
/// as possible. It's less ergonomic than an iterator, but it permits the
/// caller to reuse the `ByteRecord` allocation, which usually results
/// in higher throughput.
///
/// Records read via this method are guaranteed to have a position set
/// on them, even if the reader is at EOF or if an error is returned.
///
/// # Example
///
/// ```
/// use std::error::Error;
/// use csv_async::{ByteRecord, AsyncReader};
///
/// # fn main() { async_std::task::block_on(async {example().await.unwrap()}); }
/// async fn example() -> Result<(), Box<dyn Error>> {
/// let data = "\
/// city,country,pop
/// Boston,United States,4628910
/// ";
/// let mut rdr = AsyncReader::from_reader(data.as_bytes());
/// let mut record = ByteRecord::new();
///
/// if rdr.read_byte_record(&mut record).await? {
/// assert_eq!(record, vec!["Boston", "United States", "4628910"]);
/// Ok(())
/// } else {
/// Err(From::from("expected at least one record but got none"))
/// }
/// }
/// ```
#[inline]
pub async fn read_byte_record(&mut self, record: &mut ByteRecord) -> Result<bool> {
self.0.read_byte_record(record).await
}
/// Return the current position of this CSV reader.
///
/// The byte offset in the position returned can be used to `seek` this
/// reader. In particular, seeking to a position returned here on the same
/// data will result in parsing the same subsequent record.
///
/// # Example: reading the position
///
/// ```
/// use std::error::Error;
/// use futures::io;
/// use futures::stream::StreamExt;
/// use csv_async::{AsyncReader, Position};
///
/// # fn main() { async_std::task::block_on(async {example().await.unwrap()}); }
/// async fn example() -> Result<(), Box<dyn Error>> {
/// let data = "\
/// city,country,popcount
/// Boston,United States,4628910
/// Concord,United States,42695
/// ";
/// let rdr = AsyncReader::from_reader(io::Cursor::new(data));
/// let mut iter = rdr.into_records();
/// let mut pos = Position::new();
/// loop {
/// let next = iter.next().await;
/// if let Some(next) = next {
/// pos = next?.position().expect("Cursor should be at some valid position").clone();
/// } else {
/// break;
/// }
/// }
///
/// // `pos` should now be the position immediately before the last
/// // record.
/// assert_eq!(pos.byte(), 51);
/// assert_eq!(pos.line(), 3);
/// assert_eq!(pos.record(), 2);
/// Ok(())
/// }
/// ```
#[inline]
pub fn position(&self) -> &Position {
self.0.position()
}
/// Returns true if and only if this reader has been exhausted.
///
/// When this returns true, no more records can be read from this reader
/// (unless it has been seeked to another position).
///
/// # Example
///
/// ```
/// use std::error::Error;
/// use futures::io;
/// use futures::stream::StreamExt;
/// use csv_async::{AsyncReader, Position};
///
/// # fn main() { async_std::task::block_on(async {example().await.unwrap()}); }
/// async fn example() -> Result<(), Box<dyn Error>> {
/// let data = "\
/// city,country,popcount
/// Boston,United States,4628910
/// Concord,United States,42695
/// ";
/// let mut rdr = AsyncReader::from_reader(io::Cursor::new(data));
/// assert!(!rdr.is_done());
/// {
/// let mut records = rdr.records();
/// while let Some(record) = records.next().await {
/// let _ = record?;
/// }
/// }
/// assert!(rdr.is_done());
/// Ok(())
/// }
/// ```
#[inline]
pub fn is_done(&self) -> bool {
self.0.is_done()
}
/// Returns true if and only if this reader has been configured to
/// interpret the first record as a header record.
#[inline]
pub fn has_headers(&self) -> bool {
self.0.has_headers()
}
/// Returns a reference to the underlying reader.
#[inline]
pub fn get_ref(&self) -> &R {
self.0.get_ref()
}
/// Returns a mutable reference to the underlying reader.
#[inline]
pub fn get_mut(&mut self) -> &mut R {
self.0.get_mut()
}
/// Unwraps this CSV reader, returning the underlying reader.
///
/// Note that any leftover data inside this reader's internal buffer is
/// lost.
#[inline]
pub fn into_inner(self) -> R {
self.0.into_inner()
}
}
impl<R: io::AsyncRead + io::AsyncSeek + std::marker::Unpin> AsyncReader<R> {
/// Seeks the underlying reader to the position given.
///
/// This comes with a few caveats:
///
/// * Any internal buffer associated with this reader is cleared.
/// * If the given position does not correspond to a position immediately
/// before the start of a record, then the behavior of this reader is
/// unspecified.
/// * Any special logic that skips the first record in the CSV reader
/// when reading or iterating over records is disabled.
///
/// If the given position has a byte offset equivalent to the current
/// position, then no seeking is performed.
///
/// If the header row has not already been read, then this will attempt
/// to read the header row before seeking. Therefore, it is possible that
/// this returns an error associated with reading CSV data.
///
/// Note that seeking is performed based only on the byte offset in the
/// given position. Namely, the record or line numbers in the position may
/// be incorrect, but this will cause any future position generated by
/// this CSV reader to be similarly incorrect.
///
/// # Example: seek to parse a record twice
///
/// ```
/// use std::error::Error;
/// use futures::io;
/// use futures::stream::StreamExt;
/// use csv_async::{AsyncReader, Position};
///
/// # fn main() { async_std::task::block_on(async {example().await.unwrap()}); }
/// async fn example() -> Result<(), Box<dyn Error>> {
/// let data = "\
/// city,country,popcount
/// Boston,United States,4628910
/// Concord,United States,42695
/// ";
/// let mut rdr = AsyncReader::from_reader(io::Cursor::new(data));
/// let mut pos = Position::new();
/// {
/// let mut records = rdr.records();
/// loop {
/// let next = records.next().await;
/// if let Some(next) = next {
/// pos = next?.position().expect("Cursor should be at some valid position").clone();
/// } else {
/// break;
/// }
/// }
/// }
///
/// {
/// // Now seek the reader back to `pos`. This will let us read the
/// // last record again.
/// rdr.seek(pos).await?;
/// let mut records = rdr.into_records();
/// if let Some(result) = records.next().await {
/// let record = result?;
/// assert_eq!(record, vec!["Concord", "United States", "42695"]);
/// Ok(())
/// } else {
/// Err(From::from("expected at least one record but got none"))
/// }
/// }
/// }
/// ```
#[inline]
pub async fn seek(&mut self, pos: Position) -> Result<()> {
self.0.seek(pos).await
}
/// This is like `seek`, but provides direct control over how the seeking
/// operation is performed via `io::SeekFrom`.
///
/// The `pos` position given *should* correspond the position indicated
/// by `seek_from`, but there is no requirement. If the `pos` position
/// given is incorrect, then the position information returned by this
/// reader will be similarly incorrect.
///
/// If the header row has not already been read, then this will attempt
/// to read the header row before seeking. Therefore, it is possible that
/// this returns an error associated with reading CSV data.
///
/// Unlike `seek`, this will always cause an actual seek to be performed.
#[inline]
pub async fn seek_raw(
&mut self,
seek_from: io::SeekFrom,
pos: Position,
) -> Result<()> {
self.0.seek_raw(seek_from, pos).await
}
/// Rewinds the underlying reader to first data record.
///
/// Function is aware of header presence.
/// After `rewind` record iterators will return first data record (skipping header if present), while
/// after `seek(0)` they will return header row (even if `has_header` is set).
///
/// # Example: Reads the same data multiply times
///
/// ```
/// use std::error::Error;
/// use futures::io;
/// use futures::stream::StreamExt;
/// use csv_async::AsyncReader;
///
/// # fn main() { async_std::task::block_on(async {example().await.unwrap()}); }
/// async fn example() -> Result<(), Box<dyn Error>> {
/// let data = "\
/// city,country,popcount
/// Boston,United States,4628910
/// Concord,United States,42695
/// ";
/// let mut rdr = AsyncReader::from_reader(io::Cursor::new(data));
/// let mut output = Vec::new();
/// loop {
/// let mut records = rdr.records();
/// while let Some(rec) = records.next().await {
/// output.push(rec?);
/// }
/// if output.len() >= 6 {
/// break;
/// } else {
/// drop(records);
/// rdr.rewind().await?;
/// }
/// }
/// assert_eq!(output,
/// vec![
/// vec!["Boston", "United States", "4628910"],
/// vec!["Concord", "United States", "42695"],
/// vec!["Boston", "United States", "4628910"],
/// vec!["Concord", "United States", "42695"],
/// vec!["Boston", "United States", "4628910"],
/// vec!["Concord", "United States", "42695"],
/// ]);
/// Ok(())
/// }
/// ```
#[inline]
pub async fn rewind(&mut self) -> Result<()> {
self.0.rewind().await
}
}
#[cfg(test)]
mod tests {
use std::pin::Pin;
use std::task::{Context, Poll};
use futures::io;
use futures::stream::StreamExt;
use async_std::task;
use crate::byte_record::ByteRecord;
use crate::error::ErrorKind;
use crate::string_record::StringRecord;
use crate::Trim;
use super::{Position, AsyncReaderBuilder, AsyncReader};
fn b(s: &str) -> &[u8] {
s.as_bytes()
}
fn s(b: &[u8]) -> &str {
::std::str::from_utf8(b).unwrap()
}
fn newpos(byte: u64, line: u64, record: u64) -> Position {
let mut p = Position::new();
p.set_byte(byte).set_line(line).set_record(record);
p
}
async fn count(stream: impl StreamExt) -> usize {
stream.fold(0, |acc, _| async move { acc + 1 }).await
}
#[async_std::test]
async fn read_byte_record() {
let data = b("foo,\"b,ar\",baz\nabc,mno,xyz");
let mut rdr =
AsyncReaderBuilder::new().has_headers(false).create_reader(data);
let mut rec = ByteRecord::new();
assert!(rdr.read_byte_record(&mut rec).await.unwrap());
assert_eq!(3, rec.len());
assert_eq!("foo", s(&rec[0]));
assert_eq!("b,ar", s(&rec[1]));
assert_eq!("baz", s(&rec[2]));
assert!(rdr.read_byte_record(&mut rec).await.unwrap());
assert_eq!(3, rec.len());
assert_eq!("abc", s(&rec[0]));
assert_eq!("mno", s(&rec[1]));
assert_eq!("xyz", s(&rec[2]));
assert!(!rdr.read_byte_record(&mut rec).await.unwrap());
}
#[async_std::test]
async fn read_trimmed_records_and_headers() {
let data = b("foo, bar,\tbaz\n 1, 2, 3\n1\t,\t,3\t\t");
let mut rdr = AsyncReaderBuilder::new()
.has_headers(true)
.trim(Trim::All)
.create_reader(data);
let mut rec = ByteRecord::new();
assert!(rdr.read_byte_record(&mut rec).await.unwrap());
assert_eq!("1", s(&rec[0]));
assert_eq!("2", s(&rec[1]));
assert_eq!("3", s(&rec[2]));
let mut rec = StringRecord::new();
assert!(rdr.read_record(&mut rec).await.unwrap());
assert_eq!("1", &rec[0]);
assert_eq!("", &rec[1]);
assert_eq!("3", &rec[2]);
{
let headers = rdr.headers().await.unwrap();
assert_eq!(3, headers.len());
assert_eq!("foo", &headers[0]);
assert_eq!("bar", &headers[1]);
assert_eq!("baz", &headers[2]);
}
}
#[async_std::test]
async fn read_trimmed_header() {
let data = b("foo, bar,\tbaz\n 1, 2, 3\n1\t,\t,3\t\t");
let mut rdr = AsyncReaderBuilder::new()
.has_headers(true)
.trim(Trim::Headers)
.create_reader(data);
let mut rec = ByteRecord::new();
assert!(rdr.read_byte_record(&mut rec).await.unwrap());
assert_eq!(" 1", s(&rec[0]));
assert_eq!(" 2", s(&rec[1]));
assert_eq!(" 3", s(&rec[2]));
{
let headers = rdr.headers().await.unwrap();
assert_eq!(3, headers.len());
assert_eq!("foo", &headers[0]);
assert_eq!("bar", &headers[1]);
assert_eq!("baz", &headers[2]);
}
}
#[async_std::test]
async fn read_trimed_header_invalid_utf8() {
let data = &b"foo, b\xFFar,\tbaz\na,b,c\nd,e,f"[..];
let mut rdr = AsyncReaderBuilder::new()
.has_headers(true)
.trim(Trim::Headers)
.create_reader(data);
let mut rec = StringRecord::new();
// force the headers to be read
let _ = rdr.read_record(&mut rec).await;
// Check the byte headers are trimmed
{
let headers = rdr.byte_headers().await.unwrap();
assert_eq!(3, headers.len());
assert_eq!(b"foo", &headers[0]);
assert_eq!(b"b\xFFar", &headers[1]);
assert_eq!(b"baz", &headers[2]);
}
match *rdr.headers().await.unwrap_err().kind() {
ErrorKind::Utf8 { pos: Some(ref pos), ref err } => {
assert_eq!(pos, &newpos(0, 1, 0));
assert_eq!(err.field(), 1);
assert_eq!(err.valid_up_to(), 3);
}
ref err => panic!("match failed, got {:?}", err),
}
}
#[async_std::test]
async fn read_trimmed_records() {
let data = b("foo, bar,\tbaz\n 1, 2, 3\n1\t,\t,3\t\t");
let mut rdr = AsyncReaderBuilder::new()
.has_headers(true)
.trim(Trim::Fields)
.create_reader(data);
let mut rec = ByteRecord::new();
assert!(rdr.read_byte_record(&mut rec).await.unwrap());
assert_eq!("1", s(&rec[0]));
assert_eq!("2", s(&rec[1]));
assert_eq!("3", s(&rec[2]));
{
let headers = rdr.headers().await.unwrap();
assert_eq!(3, headers.len());
assert_eq!("foo", &headers[0]);
assert_eq!(" bar", &headers[1]);
assert_eq!("\tbaz", &headers[2]);
}
}
#[async_std::test]
async fn read_record_unequal_fails() {
let data = b("foo\nbar,baz");
let mut rdr =
AsyncReaderBuilder::new().has_headers(false).create_reader(data);
let mut rec = ByteRecord::new();
assert!(rdr.read_byte_record(&mut rec).await.unwrap());
assert_eq!(1, rec.len());
assert_eq!("foo", s(&rec[0]));
match rdr.read_byte_record(&mut rec).await {
Err(err) => match *err.kind() {
ErrorKind::UnequalLengths {
expected_len: 1,
ref pos,
len: 2,
} => {
assert_eq!(pos, &Some(newpos(4, 2, 1)));
}
ref wrong => panic!("match failed, got {:?}", wrong),
},
wrong => panic!("match failed, got {:?}", wrong),
}
}
#[async_std::test]
async fn read_record_unequal_ok() {
let data = b("foo\nbar,baz");
let mut rdr = AsyncReaderBuilder::new()
.has_headers(false)
.flexible(true)
.create_reader(data);
let mut rec = ByteRecord::new();
assert!(rdr.read_byte_record(&mut rec).await.unwrap());
assert_eq!(1, rec.len());
assert_eq!("foo", s(&rec[0]));
assert!(rdr.read_byte_record(&mut rec).await.unwrap());
assert_eq!(2, rec.len());
assert_eq!("bar", s(&rec[0]));
assert_eq!("baz", s(&rec[1]));
assert!(!rdr.read_byte_record(&mut rec).await.unwrap());
}
// This tests that even if we get a CSV error, we can continue reading
// if we want.
#[async_std::test]
async fn read_record_unequal_continue() {
let data = b("foo\nbar,baz\nquux");
let mut rdr =
AsyncReaderBuilder::new().has_headers(false).create_reader(data);
let mut rec = ByteRecord::new();
assert!(rdr.read_byte_record(&mut rec).await.unwrap());
assert_eq!(1, rec.len());
assert_eq!("foo", s(&rec[0]));
match rdr.read_byte_record(&mut rec).await {
Err(err) => match err.kind() {
&ErrorKind::UnequalLengths {
expected_len: 1,
ref pos,
len: 2,
} => {
assert_eq!(pos, &Some(newpos(4, 2, 1)));
}
wrong => panic!("match failed, got {:?}", wrong),
},
wrong => panic!("match failed, got {:?}", wrong),
}
assert!(rdr.read_byte_record(&mut rec).await.unwrap());
assert_eq!(1, rec.len());
assert_eq!("quux", s(&rec[0]));
assert!(!rdr.read_byte_record(&mut rec).await.unwrap());
}
#[async_std::test]
async fn read_record_headers() {
let data = b("foo,bar,baz\na,b,c\nd,e,f");
let mut rdr = AsyncReaderBuilder::new().has_headers(true).create_reader(data);
let mut rec = StringRecord::new();
assert!(rdr.read_record(&mut rec).await.unwrap());
assert_eq!(3, rec.len());
assert_eq!("a", &rec[0]);
assert!(rdr.read_record(&mut rec).await.unwrap());
assert_eq!(3, rec.len());
assert_eq!("d", &rec[0]);
assert!(!rdr.read_record(&mut rec).await.unwrap());
{
let headers = rdr.byte_headers().await.unwrap();
assert_eq!(3, headers.len());
assert_eq!(b"foo", &headers[0]);
assert_eq!(b"bar", &headers[1]);
assert_eq!(b"baz", &headers[2]);
}
{
let headers = rdr.headers().await.unwrap();
assert_eq!(3, headers.len());
assert_eq!("foo", &headers[0]);
assert_eq!("bar", &headers[1]);
assert_eq!("baz", &headers[2]);
}
}
#[async_std::test]
async fn read_record_headers_invalid_utf8() {
let data = &b"foo,b\xFFar,baz\na,b,c\nd,e,f"[..];
let mut rdr = AsyncReaderBuilder::new().has_headers(true).create_reader(data);
let mut rec = StringRecord::new();
assert!(rdr.read_record(&mut rec).await.unwrap());
assert_eq!(3, rec.len());
assert_eq!("a", &rec[0]);
assert!(rdr.read_record(&mut rec).await.unwrap());
assert_eq!(3, rec.len());
assert_eq!("d", &rec[0]);
assert!(!rdr.read_record(&mut rec).await.unwrap());
// Check that we can read the headers as raw bytes, but that
// if we read them as strings, we get an appropriate UTF-8 error.
{
let headers = rdr.byte_headers().await.unwrap();
assert_eq!(3, headers.len());
assert_eq!(b"foo", &headers[0]);
assert_eq!(b"b\xFFar", &headers[1]);
assert_eq!(b"baz", &headers[2]);
}
match *rdr.headers().await.unwrap_err().kind() {
ErrorKind::Utf8 { pos: Some(ref pos), ref err } => {
assert_eq!(pos, &newpos(0, 1, 0));
assert_eq!(err.field(), 1);
assert_eq!(err.valid_up_to(), 1);
}
ref err => panic!("match failed, got {:?}", err),
}
}
#[async_std::test]
async fn read_record_no_headers_before() {
let data = b("foo,bar,baz\na,b,c\nd,e,f");
let mut rdr =
AsyncReaderBuilder::new().has_headers(false).create_reader(data);
let mut rec = StringRecord::new();
{
let headers = rdr.headers().await.unwrap();
assert_eq!(3, headers.len());
assert_eq!("foo", &headers[0]);
assert_eq!("bar", &headers[1]);
assert_eq!("baz", &headers[2]);
}
assert!(rdr.read_record(&mut rec).await.unwrap());
assert_eq!(3, rec.len());
assert_eq!("foo", &rec[0]);
assert!(rdr.read_record(&mut rec).await.unwrap());
assert_eq!(3, rec.len());
assert_eq!("a", &rec[0]);
assert!(rdr.read_record(&mut rec).await.unwrap());
assert_eq!(3, rec.len());
assert_eq!("d", &rec[0]);
assert!(!rdr.read_record(&mut rec).await.unwrap());
}
#[async_std::test]
async fn read_record_no_headers_after() {
let data = b("foo,bar,baz\na,b,c\nd,e,f");
let mut rdr =
AsyncReaderBuilder::new().has_headers(false).create_reader(data);
let mut rec = StringRecord::new();
assert!(rdr.read_record(&mut rec).await.unwrap());
assert_eq!(3, rec.len());
assert_eq!("foo", &rec[0]);
assert!(rdr.read_record(&mut rec).await.unwrap());
assert_eq!(3, rec.len());
assert_eq!("a", &rec[0]);
assert!(rdr.read_record(&mut rec).await.unwrap());
assert_eq!(3, rec.len());
assert_eq!("d", &rec[0]);
assert!(!rdr.read_record(&mut rec).await.unwrap());
let headers = rdr.headers().await.unwrap();
assert_eq!(3, headers.len());
assert_eq!("foo", &headers[0]);
assert_eq!("bar", &headers[1]);
assert_eq!("baz", &headers[2]);
}
#[async_std::test]
async fn seek() {
let data = b("foo,bar,baz\na,b,c\nd,e,f\ng,h,i");
let mut rdr = AsyncReaderBuilder::new().create_reader(io::Cursor::new(data));
rdr.seek(newpos(18, 3, 2)).await.unwrap();
let mut rec = StringRecord::new();
assert_eq!(18, rdr.position().byte());
assert!(rdr.read_record(&mut rec).await.unwrap());
assert_eq!(3, rec.len());
assert_eq!("d", &rec[0]);
assert_eq!(24, rdr.position().byte());
assert_eq!(4, rdr.position().line());
assert_eq!(3, rdr.position().record());
assert!(rdr.read_record(&mut rec).await.unwrap());
assert_eq!(3, rec.len());
assert_eq!("g", &rec[0]);
assert!(!rdr.read_record(&mut rec).await.unwrap());
}
// Test that we can read headers after seeking even if the headers weren't
// explicit read before seeking.
#[async_std::test]
async fn seek_headers_after() {
let data = b("foo,bar,baz\na,b,c\nd,e,f\ng,h,i");
let mut rdr = AsyncReaderBuilder::new().create_reader(io::Cursor::new(data));
rdr.seek(newpos(18, 3, 2)).await.unwrap();
assert_eq!(rdr.headers().await.unwrap(), vec!["foo", "bar", "baz"]);
}
// Test that we can read headers after seeking if the headers were read
// before seeking.
#[async_std::test]
async fn seek_headers_before_after() {
let data = b("foo,bar,baz\na,b,c\nd,e,f\ng,h,i");
let mut rdr = AsyncReaderBuilder::new().create_reader(io::Cursor::new(data));
let headers = rdr.headers().await.unwrap().clone();
rdr.seek(newpos(18, 3, 2)).await.unwrap();
assert_eq!(&headers, rdr.headers().await.unwrap());
}
// Test that even if we didn't read headers before seeking, if we seek to
// the current byte offset, then no seeking is done and therefore we can
// still read headers after seeking.
#[async_std::test]
async fn seek_headers_no_actual_seek() {
let data = b("foo,bar,baz\na,b,c\nd,e,f\ng,h,i");
let mut rdr = AsyncReaderBuilder::new().create_reader(io::Cursor::new(data));
rdr.seek(Position::new()).await.unwrap();
assert_eq!("foo", &rdr.headers().await.unwrap()[0]);
}
#[async_std::test]
async fn rewind() {
let data = b("foo,bar,baz\na,b,c\nd,e,f\ng,h,i");
let mut rdr = AsyncReaderBuilder::new().create_reader(io::Cursor::new(data));
// rdr.seek(newpos(18, 3, 2)).await.unwrap();
let mut rec = StringRecord::new();
assert!(rdr.read_record(&mut rec).await.unwrap());
assert_eq!(3, rec.len());
assert_eq!("a", &rec[0]);
// assert_eq!(18, rdr.position().byte());
assert!(rdr.read_record(&mut rec).await.unwrap());
assert_eq!(3, rec.len());
assert_eq!("d", &rec[0]);
rdr.rewind().await.unwrap();
assert!(rdr.read_record(&mut rec).await.unwrap());
assert_eq!(3, rec.len());
assert_eq!("a", &rec[0]);
}
// Test that position info is reported correctly in absence of headers.
#[async_std::test]
async fn positions_no_headers() {
let mut rdr = AsyncReaderBuilder::new()
.has_headers(false)
.create_reader("a,b,c\nx,y,z".as_bytes())
.into_records();
let pos = rdr.next().await.unwrap().unwrap().position().unwrap().clone();
assert_eq!(pos.byte(), 0);
assert_eq!(pos.line(), 1);
assert_eq!(pos.record(), 0);
let pos = rdr.next().await.unwrap().unwrap().position().unwrap().clone();
assert_eq!(pos.byte(), 6);
assert_eq!(pos.line(), 2);
assert_eq!(pos.record(), 1);
// Test that we are at end of stream, and properly signal this.
assert!(rdr.next().await.is_none());
// Testing that we are not panic, trying to pass over end of stream (Issue#22)
assert!(rdr.next().await.is_none());
}
// Test that position info is reported correctly with headers.
#[async_std::test]
async fn positions_headers() {
let mut rdr = AsyncReaderBuilder::new()
.has_headers(true)
.create_reader("a,b,c\nx,y,z".as_bytes())
.into_records();
let pos = rdr.next().await.unwrap().unwrap().position().unwrap().clone();
assert_eq!(pos.byte(), 6);
assert_eq!(pos.line(), 2);
assert_eq!(pos.record(), 1);
}
// Test that reading headers on empty data yields an empty record.
#[async_std::test]
async fn headers_on_empty_data() {
let mut rdr = AsyncReaderBuilder::new().create_reader("".as_bytes());
let r = rdr.byte_headers().await.unwrap();
assert_eq!(r.len(), 0);
}
// Test that reading the first record on empty data works.
#[async_std::test]
async fn no_headers_on_empty_data() {
let mut rdr =
AsyncReaderBuilder::new().has_headers(false).create_reader("".as_bytes());
assert_eq!(count(rdr.records()).await, 0);
}
// Test that reading the first record on empty data works, even if
// we've tried to read headers before hand.
#[async_std::test]
async fn no_headers_on_empty_data_after_headers() {
let mut rdr =
AsyncReaderBuilder::new().has_headers(false).create_reader("".as_bytes());
assert_eq!(rdr.headers().await.unwrap().len(), 0);
assert_eq!(count(rdr.records()).await, 0);
}
#[test]
fn behavior_on_io_errors() {
struct FailingRead;
impl io::AsyncRead for FailingRead {
fn poll_read(
self: Pin<&mut Self>,
_cx: &mut Context,
_buf: &mut [u8]
) -> Poll<Result<usize, io::Error>> {
Poll::Ready(Err(io::Error::new(io::ErrorKind::Other, "Broken reader")))
}
}
impl std::marker::Unpin for FailingRead {}
task::block_on(async {
let mut records = AsyncReader::from_reader(FailingRead).into_records();
let first_record = records.next().await;
assert!(
matches!(&first_record, Some(Err(e)) if matches!(e.kind(), crate::ErrorKind::Io(_)))
);
assert!(records.next().await.is_none());
});
task::block_on(async {
let mut records = AsyncReaderBuilder::new()
.end_on_io_error(false)
.create_reader(FailingRead)
.into_records();
let first_record = records.next().await;
assert!(
matches!(&first_record, Some(Err(e)) if matches!(e.kind(), crate::ErrorKind::Io(_)))
);
let second_record = records.next().await;
assert!(
matches!(&second_record, Some(Err(e)) if matches!(e.kind(), crate::ErrorKind::Io(_)))
);
});
}
}