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
use std::fmt; use std::io; use std::iter::FromIterator; use std::ops::{self, Range}; use std::result; use std::str; use serde::de::Deserialize; use deserializer::deserialize_string_record; use error::{ErrorKind, FromUtf8Error, Result, new_error, new_from_utf8_error}; use reader::Reader; use byte_record::{self, ByteRecord, ByteRecordIter, Position}; /// A safe function for reading CSV data into a `StringRecord`. /// /// This relies on the internal representation of `StringRecord`. #[inline(always)] pub fn read<R: io::Read>( rdr: &mut Reader<R>, record: &mut StringRecord, ) -> Result<bool> { // TODO(burntsushi): Define this as a method using `pub(crate)` when that // stabilizes. // SAFETY: Note that despite the absence of `unsafe` in this function, this // code is critical to upholding the safety of other `unsafe` blocks in // this module. Namely, after calling `read_byte_record`, it is possible // for `record` to contain invalid UTF-8. We check for this in the // `validate` method, and if it does have invalid UTF-8, we clear the // record. (It is bad for `record` to contain invalid UTF-8 because other // accessor methods, like `get`, assume that every field is valid UTF-8.) let pos = rdr.position().clone(); let read_res = rdr.read_byte_record(&mut record.0); let utf8_res = match byte_record::validate(&record.0) { Ok(()) => Ok(()), Err(err) => { // If this record isn't valid UTF-8, then completely wipe it. record.0.clear(); Err(err) } }; match (read_res, utf8_res) { (Err(err), _) => Err(err), (Ok(_), Err(err)) => { Err(new_error(ErrorKind::Utf8 { pos: Some(pos), err: err })) } (Ok(eof), Ok(())) => Ok(eof), } } /// A single CSV record stored as valid UTF-8 bytes. /// /// A string record permits reading or writing CSV rows that are valid UTF-8. /// If string records are used to read CSV data that is not valid UTF-8, then /// the CSV reader will return an invalid UTF-8 error. If you do need to read /// possibly invalid UTF-8 data, then you should prefer using a /// [`ByteRecord`](struct.ByteRecord.html), /// since it makes no assumptions about UTF-8. /// /// If you are using the Serde (de)serialization APIs, then you probably never /// need to interact with a `ByteRecord` or a `StringRecord`. /// /// Two `StringRecord`s are compared on the basis of their field data. Any /// position information associated with the records is ignored. #[derive(Clone, Eq)] pub struct StringRecord(ByteRecord); impl PartialEq for StringRecord { fn eq(&self, other: &StringRecord) -> bool { self.as_slice() == other.as_slice() } } impl<T: AsRef<[u8]>> PartialEq<Vec<T>> for StringRecord { fn eq(&self, other: &Vec<T>) -> bool { byte_record::eq(&self.0, other) } } impl<'a, T: AsRef<[u8]>> PartialEq<Vec<T>> for &'a StringRecord { fn eq(&self, other: &Vec<T>) -> bool { byte_record::eq(&self.0, other) } } impl<T: AsRef<[u8]>> PartialEq<[T]> for StringRecord { fn eq(&self, other: &[T]) -> bool { byte_record::eq(&self.0, other) } } impl<'a, T: AsRef<[u8]>> PartialEq<[T]> for &'a StringRecord { fn eq(&self, other: &[T]) -> bool { byte_record::eq(&self.0, other) } } impl fmt::Debug for StringRecord { fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result { let fields: Vec<&str> = self.iter().collect(); write!(f, "StringRecord({:?})", fields) } } impl Default for StringRecord { #[inline] fn default() -> StringRecord { StringRecord::new() } } impl StringRecord { /// Create a new empty `StringRecord`. /// /// Note that you may find the `StringRecord::from` constructor more /// convenient, which is provided by an impl on the `From` trait. /// /// # Example: create an empty record /// /// ``` /// use csv::StringRecord; /// /// let record = StringRecord::new(); /// assert_eq!(record.len(), 0); /// ``` /// /// # Example: initialize a record from a `Vec` /// /// ``` /// use csv::StringRecord; /// /// let record = StringRecord::from(vec!["a", "b", "c"]); /// assert_eq!(record.len(), 3); /// ``` #[inline] pub fn new() -> StringRecord { StringRecord(ByteRecord::new()) } /// Create a new empty `StringRecord` with the given capacity. /// /// `buffer` refers to the capacity of the buffer used to store the /// actual row contents. `fields` refers to the number of fields one /// might expect to store. #[inline] pub fn with_capacity(buffer: usize, fields: usize) -> StringRecord { StringRecord(ByteRecord::with_capacity(buffer, fields)) } /// Create a new `StringRecord` from a `ByteRecord`. /// /// Note that this does UTF-8 validation. If the given `ByteRecord` does /// not contain valid UTF-8, then this returns an error. The error includes /// the UTF-8 error and the original `ByteRecord`. /// /// # Example: valid UTF-8 /// /// ``` /// extern crate csv; /// /// use std::error::Error; /// use csv::{ByteRecord, StringRecord}; /// /// # fn main() { example().unwrap(); } /// fn example() -> Result<(), Box<Error>> { /// let byte_record = ByteRecord::from(vec!["a", "b", "c"]); /// let str_record = StringRecord::from_byte_record(byte_record)?; /// assert_eq!(str_record.len(), 3); /// Ok(()) /// } /// ``` /// /// # Example: invalid UTF-8 /// /// ``` /// use csv::{ByteRecord, StringRecord}; /// /// let byte_record = ByteRecord::from(vec![ /// &b"quux"[..], &b"foo\xFFbar"[..], &b"c"[..], /// ]); /// let err = StringRecord::from_byte_record(byte_record).unwrap_err(); /// assert_eq!(err.utf8_error().field(), 1); /// assert_eq!(err.utf8_error().valid_up_to(), 3); /// ``` #[inline] pub fn from_byte_record( record: ByteRecord, ) -> result::Result<StringRecord, FromUtf8Error> { match byte_record::validate(&record) { Ok(()) => Ok(StringRecord(record)), Err(err) => Err(new_from_utf8_error(record, err)), } } /// Lossily create a new `StringRecord` from a `ByteRecord`. /// /// This is like `StringRecord::from_byte_record`, except all invalid UTF-8 /// sequences are replaced with the `U+FFFD REPLACEMENT CHARACTER`, which /// looks like this: �. /// /// # Example: valid UTF-8 /// /// ``` /// use csv::{ByteRecord, StringRecord}; /// /// let byte_record = ByteRecord::from(vec!["a", "b", "c"]); /// let str_record = StringRecord::from_byte_record_lossy(byte_record); /// assert_eq!(str_record.len(), 3); /// ``` /// /// # Example: invalid UTF-8 /// /// ``` /// use csv::{ByteRecord, StringRecord}; /// /// let byte_record = ByteRecord::from(vec![ /// &b"quux"[..], &b"foo\xFFbar"[..], &b"c"[..], /// ]); /// let str_record = StringRecord::from_byte_record_lossy(byte_record); /// assert_eq!(&str_record[0], "quux"); /// assert_eq!(&str_record[1], "foo�bar"); /// assert_eq!(&str_record[2], "c"); /// ``` #[inline] pub fn from_byte_record_lossy(record: ByteRecord) -> StringRecord { // If the record is valid UTF-8, then take the easy path. if let Ok(()) = byte_record::validate(&record) { return StringRecord(record); } // TODO: We can be faster here. Not sure if it's worth it. let mut str_record = StringRecord::with_capacity( record.as_slice().len(), record.len()); for field in &record { str_record.push_field(&String::from_utf8_lossy(field)); } str_record } /// Deserialize this record. /// /// The `D` type parameter refers to the type that this record should be /// deserialized into. The `'de` lifetime refers to the lifetime of the /// `StringRecord`. The `'de` lifetime permits deserializing into structs /// that borrow field data from this record. /// /// An optional `headers` parameter permits deserializing into a struct /// based on its field names (corresponding to header values) rather than /// the order in which the fields are defined. /// /// # Example: without headers /// /// This shows how to deserialize a single row into a struct based on the /// order in which fields occur. This example also shows how to borrow /// fields from the `StringRecord`, which results in zero allocation /// deserialization. /// /// ``` /// extern crate csv; /// #[macro_use] /// extern crate serde_derive; /// /// use std::error::Error; /// use csv::StringRecord; /// /// #[derive(Deserialize)] /// struct Row<'a> { /// city: &'a str, /// country: &'a str, /// population: u64, /// } /// /// # fn main() { example().unwrap() } /// fn example() -> Result<(), Box<Error>> { /// let record = StringRecord::from(vec![ /// "Boston", "United States", "4628910", /// ]); /// /// let row: Row = record.deserialize(None)?; /// assert_eq!(row.city, "Boston"); /// assert_eq!(row.country, "United States"); /// assert_eq!(row.population, 4628910); /// Ok(()) /// } /// ``` /// /// # Example: with headers /// /// This example is like the previous one, but shows how to deserialize /// into a struct based on the struct's field names. For this to work, /// you must provide a header row. /// /// This example also shows that you can deserialize into owned data /// types (e.g., `String`) instead of borrowed data types (e.g., `&str`). /// /// ``` /// extern crate csv; /// #[macro_use] /// extern crate serde_derive; /// /// use std::error::Error; /// use csv::StringRecord; /// /// #[derive(Deserialize)] /// struct Row { /// city: String, /// country: String, /// population: u64, /// } /// /// # fn main() { example().unwrap() } /// fn example() -> Result<(), Box<Error>> { /// // Notice that the fields are not in the same order /// // as the fields in the struct! /// let header = StringRecord::from(vec![ /// "country", "city", "population", /// ]); /// let record = StringRecord::from(vec![ /// "United States", "Boston", "4628910", /// ]); /// /// let row: Row = record.deserialize(Some(&header))?; /// assert_eq!(row.city, "Boston"); /// assert_eq!(row.country, "United States"); /// assert_eq!(row.population, 4628910); /// Ok(()) /// } /// ``` pub fn deserialize<'de, D: Deserialize<'de>>( &'de self, headers: Option<&'de StringRecord>, ) -> Result<D> { deserialize_string_record(self, headers) } /// Returns an iterator over all fields in this record. /// /// # Example /// /// This example shows how to iterate over each field in a `StringRecord`. /// /// ``` /// use csv::StringRecord; /// /// let record = StringRecord::from(vec!["a", "b", "c"]); /// for field in record.iter() { /// assert!(field == "a" || field == "b" || field == "c"); /// } /// ``` #[inline] pub fn iter(&self) -> StringRecordIter { self.into_iter() } /// Return the field at index `i`. /// /// If no field at index `i` exists, then this returns `None`. /// /// # Example /// /// ``` /// use csv::StringRecord; /// /// let record = StringRecord::from(vec!["a", "b", "c"]); /// assert_eq!(record.get(1), Some("b")); /// assert_eq!(record.get(3), None); /// ``` #[inline] pub fn get(&self, i: usize) -> Option<&str> { self.0.get(i).map(|bytes| { // This is safe because we guarantee that all string records // have a valid UTF-8 buffer. It's also safe because we // individually check each field for valid UTF-8. unsafe { str::from_utf8_unchecked(bytes) } }) } /// Returns true if and only if this record is empty. /// /// # Example /// /// ``` /// use csv::StringRecord; /// /// assert!(StringRecord::new().is_empty()); /// ``` #[inline] pub fn is_empty(&self) -> bool { self.len() == 0 } /// Returns the number of fields in this record. /// /// # Example /// /// ``` /// use csv::StringRecord; /// /// let record = StringRecord::from(vec!["a", "b", "c"]); /// assert_eq!(record.len(), 3); /// ``` #[inline] pub fn len(&self) -> usize { self.0.len() } /// Truncate this record to `n` fields. /// /// If `n` is greater than the number of fields in this record, then this /// has no effect. /// /// # Example /// /// ``` /// use csv::StringRecord; /// /// let mut record = StringRecord::from(vec!["a", "b", "c"]); /// assert_eq!(record.len(), 3); /// record.truncate(1); /// assert_eq!(record.len(), 1); /// assert_eq!(record, vec!["a"]); /// ``` #[inline] pub fn truncate(&mut self, n: usize) { self.0.truncate(n); } /// Clear this record so that it has zero fields. /// /// Note that it is not necessary to clear the record to reuse it with /// the CSV reader. /// /// # Example /// /// ``` /// use csv::StringRecord; /// /// let mut record = StringRecord::from(vec!["a", "b", "c"]); /// assert_eq!(record.len(), 3); /// record.clear(); /// assert_eq!(record.len(), 0); /// ``` #[inline] pub fn clear(&mut self) { self.0.clear(); } /// Trim the fields of this record so that leading and trailing whitespace /// is removed. /// /// This method uses the Unicode definition of whitespace. /// /// # Example /// /// ``` /// use csv::StringRecord; /// /// let mut record = StringRecord::from(vec![ /// " ", "\u{3000}\tfoo ", "bar ", "b a z", /// ]); /// record.trim(); /// assert_eq!(record, vec!["", "foo", "bar", "b a z"]); /// ``` pub fn trim(&mut self) { let length = self.len(); if length == 0 { return; } // TODO: We could likely do this in place, but for now, we allocate. let mut trimmed = StringRecord::with_capacity( self.as_slice().len(), self.len()); for mut field in &*self { trimmed.push_field(field.trim()); } *self = trimmed; } /// Add a new field to this record. /// /// # Example /// /// ``` /// use csv::StringRecord; /// /// let mut record = StringRecord::new(); /// record.push_field("foo"); /// assert_eq!(&record[0], "foo"); /// ``` #[inline] pub fn push_field(&mut self, field: &str) { self.0.push_field(field.as_bytes()); } /// Return the position of this record, if available. /// /// # Example /// /// ``` /// extern crate csv; /// /// use std::error::Error; /// use csv::{StringRecord, ReaderBuilder}; /// /// # fn main() { example().unwrap(); } /// fn example() -> Result<(), Box<Error>> { /// let mut record = StringRecord::new(); /// let mut rdr = ReaderBuilder::new() /// .has_headers(false) /// .from_reader("a,b,c\nx,y,z".as_bytes()); /// /// assert!(rdr.read_record(&mut record)?); /// { /// let pos = record.position().expect("a record position"); /// assert_eq!(pos.byte(), 0); /// assert_eq!(pos.line(), 1); /// assert_eq!(pos.record(), 0); /// } /// /// assert!(rdr.read_record(&mut record)?); /// { /// let pos = record.position().expect("a record position"); /// assert_eq!(pos.byte(), 6); /// assert_eq!(pos.line(), 2); /// assert_eq!(pos.record(), 1); /// } /// /// // Finish the CSV reader for good measure. /// assert!(!rdr.read_record(&mut record)?); /// Ok(()) /// } /// ``` #[inline] pub fn position(&self) -> Option<&Position> { self.0.position() } /// Set the position of this record. /// /// # Example /// /// ``` /// use csv::{StringRecord, Position}; /// /// let mut record = StringRecord::from(vec!["a", "b", "c"]); /// let mut pos = Position::new(); /// pos.set_byte(100); /// pos.set_line(4); /// pos.set_record(2); /// /// record.set_position(Some(pos.clone())); /// assert_eq!(record.position(), Some(&pos)); /// ``` #[inline] pub fn set_position(&mut self, pos: Option<Position>) { self.0.set_position(pos); } /// Return the start and end position of a field in this record. /// /// If no such field exists at the given index, then return `None`. /// /// The range returned can be used with the slice returned by `as_slice`. /// Namely, the range returned is guaranteed to start and end at valid /// UTF-8 sequence boundaries. /// /// # Example /// /// ``` /// use csv::StringRecord; /// /// let record = StringRecord::from(vec!["foo", "quux", "z"]); /// let range = record.range(1).expect("a record range"); /// assert_eq!(&record.as_slice()[range], "quux"); /// ``` #[inline] pub fn range(&self, i: usize) -> Option<Range<usize>> { self.0.range(i) } /// Return the entire row as a single string slice. The slice returned /// stores all fields contiguously. The boundaries of each field can be /// determined via the `range` method. /// /// # Example /// /// ``` /// use csv::StringRecord; /// /// let record = StringRecord::from(vec!["foo", "quux", "z"]); /// assert_eq!(record.as_slice(), "fooquuxz"); /// ``` #[inline] pub fn as_slice(&self) -> &str { // This is safe because we guarantee that each field is valid UTF-8. // If each field is valid UTF-8, then the entire buffer (up to the end // of the last field) must also be valid UTF-8. unsafe { str::from_utf8_unchecked(self.0.as_slice()) } } /// Return a reference to this record's raw /// [`ByteRecord`](struct.ByteRecord.html). /// /// # Example /// /// ``` /// use csv::StringRecord; /// /// let str_record = StringRecord::from(vec!["a", "b", "c"]); /// let byte_record = str_record.as_byte_record(); /// assert_eq!(&byte_record[2], b"c"); /// ``` #[inline] pub fn as_byte_record(&self) -> &ByteRecord { &self.0 } /// Convert this `StringRecord` into a /// [`ByteRecord`](struct.ByteRecord.html). /// /// # Example /// /// ``` /// use csv::StringRecord; /// /// let str_record = StringRecord::from(vec!["a", "b", "c"]); /// let byte_record = str_record.into_byte_record(); /// assert_eq!(&byte_record[2], b"c"); /// ``` /// /// Note that this can also be achieved using the `From` impl: /// /// ``` /// use csv::{ByteRecord, StringRecord}; /// /// // Using ByteRecord::from... /// let str_record = StringRecord::from(vec!["a", "b", "c"]); /// assert_eq!(ByteRecord::from(str_record).len(), 3); /// /// // Using StringRecord::into... /// let str_record = StringRecord::from(vec!["a", "b", "c"]); /// let byte_record: ByteRecord = str_record.into(); /// assert_eq!(byte_record.len(), 3); /// ``` #[inline] pub fn into_byte_record(self) -> ByteRecord { self.0 } } impl ops::Index<usize> for StringRecord { type Output = str; #[inline] fn index(&self, i: usize) -> &str { self.get(i).unwrap() } } impl<T: AsRef<str>> From<Vec<T>> for StringRecord { #[inline] fn from(xs: Vec<T>) -> StringRecord { StringRecord::from_iter(xs.into_iter()) } } impl<'a, T: AsRef<str>> From<&'a [T]> for StringRecord { #[inline] fn from(xs: &'a [T]) -> StringRecord { StringRecord::from_iter(xs) } } impl<T: AsRef<str>> FromIterator<T> for StringRecord { #[inline] fn from_iter<I: IntoIterator<Item=T>>(iter: I) -> StringRecord { let mut record = StringRecord::new(); record.extend(iter); record } } impl<T: AsRef<str>> Extend<T> for StringRecord { #[inline] fn extend<I: IntoIterator<Item=T>>(&mut self, iter: I) { for x in iter { self.push_field(x.as_ref()); } } } impl<'a> IntoIterator for &'a StringRecord { type IntoIter = StringRecordIter<'a>; type Item = &'a str; #[inline] fn into_iter(self) -> StringRecordIter<'a> { StringRecordIter(self.0.iter()) } } /// An iterator over the fields in a string record. /// /// The `'r` lifetime variable refers to the lifetime of the `StringRecord` /// that is being iterated over. pub struct StringRecordIter<'r>(ByteRecordIter<'r>); impl<'r> Iterator for StringRecordIter<'r> { type Item = &'r str; #[inline] fn next(&mut self) -> Option<&'r str> { self.0.next().map(|bytes| { // See StringRecord::get for safety argument. unsafe { str::from_utf8_unchecked(bytes) } }) } #[inline] fn size_hint(&self) -> (usize, Option<usize>) { self.0.size_hint() } #[inline] fn count(self) -> usize { self.0.len() } } impl<'r> DoubleEndedIterator for StringRecordIter<'r> { #[inline] fn next_back(&mut self) -> Option<&'r str> { self.0.next_back().map(|bytes| { // See StringRecord::get for safety argument. unsafe { str::from_utf8_unchecked(bytes) } }) } } #[cfg(test)] mod tests { use string_record::StringRecord; #[test] fn trim_front() { let mut rec = StringRecord::from(vec![" abc"]); rec.trim(); assert_eq!(rec.get(0), Some("abc")); let mut rec = StringRecord::from(vec![" abc", " xyz"]); rec.trim(); assert_eq!(rec.get(0), Some("abc")); assert_eq!(rec.get(1), Some("xyz")); } #[test] fn trim_back() { let mut rec = StringRecord::from(vec!["abc "]); rec.trim(); assert_eq!(rec.get(0), Some("abc")); let mut rec = StringRecord::from(vec!["abc ", "xyz "]); rec.trim(); assert_eq!(rec.get(0), Some("abc")); assert_eq!(rec.get(1), Some("xyz")); } #[test] fn trim_both() { let mut rec = StringRecord::from(vec![" abc "]); rec.trim(); assert_eq!(rec.get(0), Some("abc")); let mut rec = StringRecord::from(vec![" abc ", " xyz "]); rec.trim(); assert_eq!(rec.get(0), Some("abc")); assert_eq!(rec.get(1), Some("xyz")); } #[test] fn trim_does_not_panic_on_empty_records_1() { let mut rec = StringRecord::from(vec![""]); rec.trim(); assert_eq!(rec.get(0), Some("")); } #[test] fn trim_does_not_panic_on_empty_records_2() { let mut rec = StringRecord::from(vec!["", ""]); rec.trim(); assert_eq!(rec.get(0), Some("")); assert_eq!(rec.get(1), Some("")); } #[test] fn trim_does_not_panic_on_empty_records_3() { let mut rec = StringRecord::new(); rec.trim(); assert_eq!(rec.as_slice().len(), 0); } #[test] fn trim_whitespace_only() { let mut rec = StringRecord::from(vec![ "\u{0009}\u{000A}\u{000B}\u{000C}\u{000D}\u{0020}\u{0085}\u{00A0}\u{1680}\u{2000}\u{2001}\u{2002}\u{2003}\u{2004}\u{2005}\u{2006}\u{2007}\u{2008}\u{2009}\u{200A}\u{2028}\u{2029}\u{202F}\u{205F}\u{3000}", ]); rec.trim(); assert_eq!(rec.get(0), Some("")); } }