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
use std::{
cell::RefCell,
cmp,
fs::File,
io::{self, Read},
path::Path,
};
use {
encoding_rs,
encoding_rs_io::DecodeReaderBytesBuilder,
grep_matcher::{LineTerminator, Match, Matcher},
};
use crate::{
line_buffer::{
self, alloc_error, BufferAllocation, LineBuffer, LineBufferBuilder,
LineBufferReader, DEFAULT_BUFFER_CAPACITY,
},
searcher::glue::{MultiLine, ReadByLine, SliceByLine},
sink::{Sink, SinkError},
};
pub use self::mmap::MmapChoice;
mod core;
mod glue;
mod mmap;
/// We use this type alias since we want the ergonomics of a matcher's `Match`
/// type, but in practice, we use it for arbitrary ranges, so give it a more
/// accurate name. This is only used in the searcher's internals.
type Range = Match;
/// The behavior of binary detection while searching.
///
/// Binary detection is the process of _heuristically_ identifying whether a
/// given chunk of data is binary or not, and then taking an action based on
/// the result of that heuristic. The motivation behind detecting binary data
/// is that binary data often indicates data that is undesirable to search
/// using textual patterns. Of course, there are many cases in which this isn't
/// true, which is why binary detection is disabled by default.
///
/// Unfortunately, binary detection works differently depending on the type of
/// search being executed:
///
/// 1. When performing a search using a fixed size buffer, binary detection is
/// applied to the buffer's contents as it is filled. Binary detection must
/// be applied to the buffer directly because binary files may not contain
/// line terminators, which could result in exorbitant memory usage.
/// 2. When performing a search using memory maps or by reading data off the
/// heap, then binary detection is only guaranteed to be applied to the
/// parts corresponding to a match. When `Quit` is enabled, then the first
/// few KB of the data are searched for binary data.
#[derive(Clone, Debug, Default)]
pub struct BinaryDetection(line_buffer::BinaryDetection);
impl BinaryDetection {
/// No binary detection is performed. Data reported by the searcher may
/// contain arbitrary bytes.
///
/// This is the default.
pub fn none() -> BinaryDetection {
BinaryDetection(line_buffer::BinaryDetection::None)
}
/// Binary detection is performed by looking for the given byte.
///
/// When searching is performed using a fixed size buffer, then the
/// contents of that buffer are always searched for the presence of this
/// byte. If it is found, then the underlying data is considered binary
/// and the search stops as if it reached EOF.
///
/// When searching is performed with the entire contents mapped into
/// memory, then binary detection is more conservative. Namely, only a
/// fixed sized region at the beginning of the contents are detected for
/// binary data. As a compromise, any subsequent matching (or context)
/// lines are also searched for binary data. If binary data is detected at
/// any point, then the search stops as if it reached EOF.
pub fn quit(binary_byte: u8) -> BinaryDetection {
BinaryDetection(line_buffer::BinaryDetection::Quit(binary_byte))
}
/// Binary detection is performed by looking for the given byte, and
/// replacing it with the line terminator configured on the searcher.
/// (If the searcher is configured to use `CRLF` as the line terminator,
/// then this byte is replaced by just `LF`.)
///
/// When searching is performed using a fixed size buffer, then the
/// contents of that buffer are always searched for the presence of this
/// byte and replaced with the line terminator. In effect, the caller is
/// guaranteed to never observe this byte while searching.
///
/// When searching is performed with the entire contents mapped into
/// memory, then this setting has no effect and is ignored.
pub fn convert(binary_byte: u8) -> BinaryDetection {
BinaryDetection(line_buffer::BinaryDetection::Convert(binary_byte))
}
/// If this binary detection uses the "quit" strategy, then this returns
/// the byte that will cause a search to quit. In any other case, this
/// returns `None`.
pub fn quit_byte(&self) -> Option<u8> {
match self.0 {
line_buffer::BinaryDetection::Quit(b) => Some(b),
_ => None,
}
}
/// If this binary detection uses the "convert" strategy, then this returns
/// the byte that will be replaced by the line terminator. In any other
/// case, this returns `None`.
pub fn convert_byte(&self) -> Option<u8> {
match self.0 {
line_buffer::BinaryDetection::Convert(b) => Some(b),
_ => None,
}
}
}
/// An encoding to use when searching.
///
/// An encoding can be used to configure a [`SearcherBuilder`] to transcode
/// source data from an encoding to UTF-8 before searching.
///
/// An `Encoding` will always be cheap to clone.
#[derive(Clone, Debug)]
pub struct Encoding(&'static encoding_rs::Encoding);
impl Encoding {
/// Create a new encoding for the specified label.
///
/// The encoding label provided is mapped to an encoding via the set of
/// available choices specified in the
/// [Encoding Standard](https://encoding.spec.whatwg.org/#concept-encoding-get).
/// If the given label does not correspond to a valid encoding, then this
/// returns an error.
pub fn new(label: &str) -> Result<Encoding, ConfigError> {
let label = label.as_bytes();
match encoding_rs::Encoding::for_label_no_replacement(label) {
Some(encoding) => Ok(Encoding(encoding)),
None => {
Err(ConfigError::UnknownEncoding { label: label.to_vec() })
}
}
}
}
/// The internal configuration of a searcher. This is shared among several
/// search related types, but is only ever written to by the SearcherBuilder.
#[derive(Clone, Debug)]
pub struct Config {
/// The line terminator to use.
line_term: LineTerminator,
/// Whether to invert matching.
invert_match: bool,
/// The number of lines after a match to include.
after_context: usize,
/// The number of lines before a match to include.
before_context: usize,
/// Whether to enable unbounded context or not.
passthru: bool,
/// Whether to count line numbers.
line_number: bool,
/// The maximum amount of heap memory to use.
///
/// When not given, no explicit limit is enforced. When set to `0`, then
/// only the memory map search strategy is available.
heap_limit: Option<usize>,
/// The memory map strategy.
mmap: MmapChoice,
/// The binary data detection strategy.
binary: BinaryDetection,
/// Whether to enable matching across multiple lines.
multi_line: bool,
/// An encoding that, when present, causes the searcher to transcode all
/// input from the encoding to UTF-8.
encoding: Option<Encoding>,
/// Whether to do automatic transcoding based on a BOM or not.
bom_sniffing: bool,
/// Whether to stop searching when a non-matching line is found after a
/// matching line.
stop_on_nonmatch: bool,
}
impl Default for Config {
fn default() -> Config {
Config {
line_term: LineTerminator::default(),
invert_match: false,
after_context: 0,
before_context: 0,
passthru: false,
line_number: true,
heap_limit: None,
mmap: MmapChoice::default(),
binary: BinaryDetection::default(),
multi_line: false,
encoding: None,
bom_sniffing: true,
stop_on_nonmatch: false,
}
}
}
impl Config {
/// Return the maximal amount of lines needed to fulfill this
/// configuration's context.
///
/// If this returns `0`, then no context is ever needed.
fn max_context(&self) -> usize {
cmp::max(self.before_context, self.after_context)
}
/// Build a line buffer from this configuration.
fn line_buffer(&self) -> LineBuffer {
let mut builder = LineBufferBuilder::new();
builder
.line_terminator(self.line_term.as_byte())
.binary_detection(self.binary.0);
if let Some(limit) = self.heap_limit {
let (capacity, additional) = if limit <= DEFAULT_BUFFER_CAPACITY {
(limit, 0)
} else {
(DEFAULT_BUFFER_CAPACITY, limit - DEFAULT_BUFFER_CAPACITY)
};
builder
.capacity(capacity)
.buffer_alloc(BufferAllocation::Error(additional));
}
builder.build()
}
}
/// An error that can occur when building a searcher.
///
/// This error occurs when a non-sensical configuration is present when trying
/// to construct a `Searcher` from a `SearcherBuilder`.
#[derive(Clone, Debug, Eq, PartialEq)]
#[non_exhaustive]
pub enum ConfigError {
/// Indicates that the heap limit configuration prevents all possible
/// search strategies from being used. For example, if the heap limit is
/// set to 0 and memory map searching is disabled or unavailable.
SearchUnavailable,
/// Occurs when a matcher reports a line terminator that is different than
/// the one configured in the searcher.
MismatchedLineTerminators {
/// The matcher's line terminator.
matcher: LineTerminator,
/// The searcher's line terminator.
searcher: LineTerminator,
},
/// Occurs when no encoding could be found for a particular label.
UnknownEncoding {
/// The provided encoding label that could not be found.
label: Vec<u8>,
},
}
impl std::error::Error for ConfigError {}
impl std::fmt::Display for ConfigError {
fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
match *self {
ConfigError::SearchUnavailable => {
write!(f, "grep config error: no available searchers")
}
ConfigError::MismatchedLineTerminators { matcher, searcher } => {
write!(
f,
"grep config error: mismatched line terminators, \
matcher has {:?} but searcher has {:?}",
matcher, searcher
)
}
ConfigError::UnknownEncoding { ref label } => write!(
f,
"grep config error: unknown encoding: {}",
String::from_utf8_lossy(label),
),
}
}
}
/// A builder for configuring a searcher.
///
/// A search builder permits specifying the configuration of a searcher,
/// including options like whether to invert the search or to enable multi
/// line search.
///
/// Once a searcher has been built, it is beneficial to reuse that searcher
/// for multiple searches, if possible.
#[derive(Clone, Debug)]
pub struct SearcherBuilder {
config: Config,
}
impl Default for SearcherBuilder {
fn default() -> SearcherBuilder {
SearcherBuilder::new()
}
}
impl SearcherBuilder {
/// Create a new searcher builder with a default configuration.
pub fn new() -> SearcherBuilder {
SearcherBuilder { config: Config::default() }
}
/// Build a searcher with the given matcher.
pub fn build(&self) -> Searcher {
let mut config = self.config.clone();
if config.passthru {
config.before_context = 0;
config.after_context = 0;
}
let mut decode_builder = DecodeReaderBytesBuilder::new();
decode_builder
.encoding(self.config.encoding.as_ref().map(|e| e.0))
.utf8_passthru(true)
.strip_bom(self.config.bom_sniffing)
.bom_override(true)
.bom_sniffing(self.config.bom_sniffing);
Searcher {
config,
decode_builder,
decode_buffer: RefCell::new(vec![0; 8 * (1 << 10)]),
line_buffer: RefCell::new(self.config.line_buffer()),
multi_line_buffer: RefCell::new(vec![]),
}
}
/// Set the line terminator that is used by the searcher.
///
/// When using a searcher, if the matcher provided has a line terminator
/// set, then it must be the same as this one. If they aren't, building
/// a searcher will return an error.
///
/// By default, this is set to `b'\n'`.
pub fn line_terminator(
&mut self,
line_term: LineTerminator,
) -> &mut SearcherBuilder {
self.config.line_term = line_term;
self
}
/// Whether to invert matching, whereby lines that don't match are reported
/// instead of reporting lines that do match.
///
/// By default, this is disabled.
pub fn invert_match(&mut self, yes: bool) -> &mut SearcherBuilder {
self.config.invert_match = yes;
self
}
/// Whether to count and include line numbers with matching lines.
///
/// This is enabled by default. There is a small performance penalty
/// associated with computing line numbers, so this can be disabled when
/// this isn't desirable.
pub fn line_number(&mut self, yes: bool) -> &mut SearcherBuilder {
self.config.line_number = yes;
self
}
/// Whether to enable multi line search or not.
///
/// When multi line search is enabled, matches *may* match across multiple
/// lines. Conversely, when multi line search is disabled, it is impossible
/// for any match to span more than one line.
///
/// **Warning:** multi line search requires having the entire contents to
/// search mapped in memory at once. When searching files, memory maps
/// will be used if possible and if they are enabled, which avoids using
/// your program's heap. However, if memory maps cannot be used (e.g.,
/// for searching streams like `stdin` or if transcoding is necessary),
/// then the entire contents of the stream are read on to the heap before
/// starting the search.
///
/// This is disabled by default.
pub fn multi_line(&mut self, yes: bool) -> &mut SearcherBuilder {
self.config.multi_line = yes;
self
}
/// Whether to include a fixed number of lines after every match.
///
/// When this is set to a non-zero number, then the searcher will report
/// `line_count` contextual lines after every match.
///
/// This is set to `0` by default.
pub fn after_context(
&mut self,
line_count: usize,
) -> &mut SearcherBuilder {
self.config.after_context = line_count;
self
}
/// Whether to include a fixed number of lines before every match.
///
/// When this is set to a non-zero number, then the searcher will report
/// `line_count` contextual lines before every match.
///
/// This is set to `0` by default.
pub fn before_context(
&mut self,
line_count: usize,
) -> &mut SearcherBuilder {
self.config.before_context = line_count;
self
}
/// Whether to enable the "passthru" feature or not.
///
/// When passthru is enabled, it effectively treats all non-matching lines
/// as contextual lines. In other words, enabling this is akin to
/// requesting an unbounded number of before and after contextual lines.
///
/// When passthru mode is enabled, any `before_context` or `after_context`
/// settings are ignored by setting them to `0`.
///
/// This is disabled by default.
pub fn passthru(&mut self, yes: bool) -> &mut SearcherBuilder {
self.config.passthru = yes;
self
}
/// Set an approximate limit on the amount of heap space used by a
/// searcher.
///
/// The heap limit is enforced in two scenarios:
///
/// * When searching using a fixed size buffer, the heap limit controls
/// how big this buffer is allowed to be. Assuming contexts are disabled,
/// the minimum size of this buffer is the length (in bytes) of the
/// largest single line in the contents being searched. If any line
/// exceeds the heap limit, then an error will be returned.
/// * When performing a multi line search, a fixed size buffer cannot be
/// used. Thus, the only choices are to read the entire contents on to
/// the heap, or use memory maps. In the former case, the heap limit set
/// here is enforced.
///
/// If a heap limit is set to `0`, then no heap space is used. If there are
/// no alternative strategies available for searching without heap space
/// (e.g., memory maps are disabled), then the searcher wil return an error
/// immediately.
///
/// By default, no limit is set.
pub fn heap_limit(
&mut self,
bytes: Option<usize>,
) -> &mut SearcherBuilder {
self.config.heap_limit = bytes;
self
}
/// Set the strategy to employ use of memory maps.
///
/// Currently, there are only two strategies that can be employed:
///
/// * **Automatic** - A searcher will use heuristics, including but not
/// limited to file size and platform, to determine whether to use memory
/// maps or not.
/// * **Never** - Memory maps will never be used. If multi line search is
/// enabled, then the entire contents will be read on to the heap before
/// searching begins.
///
/// The default behavior is **never**. Generally speaking, and perhaps
/// against conventional wisdom, memory maps don't necessarily enable
/// faster searching. For example, depending on the platform, using memory
/// maps while searching a large directory can actually be quite a bit
/// slower than using normal read calls because of the overhead of managing
/// the memory maps.
///
/// Memory maps can be faster in some cases however. On some platforms,
/// when searching a very large file that *is already in memory*, it can
/// be slightly faster to search it as a memory map instead of using
/// normal read calls.
///
/// Finally, memory maps have a somewhat complicated safety story in Rust.
/// If you aren't sure whether enabling memory maps is worth it, then just
/// don't bother with it.
///
/// **WARNING**: If your process is searching a file backed memory map
/// at the same time that file is truncated, then it's possible for the
/// process to terminate with a bus error.
pub fn memory_map(
&mut self,
strategy: MmapChoice,
) -> &mut SearcherBuilder {
self.config.mmap = strategy;
self
}
/// Set the binary detection strategy.
///
/// The binary detection strategy determines not only how the searcher
/// detects binary data, but how it responds to the presence of binary
/// data. See the [`BinaryDetection`] type for more information.
///
/// By default, binary detection is disabled.
pub fn binary_detection(
&mut self,
detection: BinaryDetection,
) -> &mut SearcherBuilder {
self.config.binary = detection;
self
}
/// Set the encoding used to read the source data before searching.
///
/// When an encoding is provided, then the source data is _unconditionally_
/// transcoded using the encoding, unless a BOM is present. If a BOM is
/// present, then the encoding indicated by the BOM is used instead. If the
/// transcoding process encounters an error, then bytes are replaced with
/// the Unicode replacement codepoint.
///
/// When no encoding is specified (the default), then BOM sniffing is
/// used (if it's enabled, which it is, by default) to determine whether
/// the source data is UTF-8 or UTF-16, and transcoding will be performed
/// automatically. If no BOM could be found, then the source data is
/// searched _as if_ it were UTF-8. However, so long as the source data is
/// at least ASCII compatible, then it is possible for a search to produce
/// useful results.
pub fn encoding(
&mut self,
encoding: Option<Encoding>,
) -> &mut SearcherBuilder {
self.config.encoding = encoding;
self
}
/// Enable automatic transcoding based on BOM sniffing.
///
/// When this is enabled and an explicit encoding is not set, then this
/// searcher will try to detect the encoding of the bytes being searched
/// by sniffing its byte-order mark (BOM). In particular, when this is
/// enabled, UTF-16 encoded files will be searched seamlessly.
///
/// When this is disabled and if an explicit encoding is not set, then
/// the bytes from the source stream will be passed through unchanged,
/// including its BOM, if one is present.
///
/// This is enabled by default.
pub fn bom_sniffing(&mut self, yes: bool) -> &mut SearcherBuilder {
self.config.bom_sniffing = yes;
self
}
/// Stop searching a file when a non-matching line is found after a
/// matching line.
///
/// This is useful for searching sorted files where it is expected that all
/// the matches will be on adjacent lines.
pub fn stop_on_nonmatch(
&mut self,
stop_on_nonmatch: bool,
) -> &mut SearcherBuilder {
self.config.stop_on_nonmatch = stop_on_nonmatch;
self
}
}
/// A searcher executes searches over a haystack and writes results to a caller
/// provided sink.
///
/// Matches are detected via implementations of the `Matcher` trait, which must
/// be provided by the caller when executing a search.
///
/// When possible, a searcher should be reused.
#[derive(Clone, Debug)]
pub struct Searcher {
/// The configuration for this searcher.
///
/// We make most of these settings available to users of `Searcher` via
/// public API methods, which can be queried in implementations of `Sink`
/// if necessary.
config: Config,
/// A builder for constructing a streaming reader that transcodes source
/// data according to either an explicitly specified encoding or via an
/// automatically detected encoding via BOM sniffing.
///
/// When no transcoding is needed, then the transcoder built will pass
/// through the underlying bytes with no additional overhead.
decode_builder: DecodeReaderBytesBuilder,
/// A buffer that is used for transcoding scratch space.
decode_buffer: RefCell<Vec<u8>>,
/// A line buffer for use in line oriented searching.
///
/// We wrap it in a RefCell to permit lending out borrows of `Searcher`
/// to sinks. We still require a mutable borrow to execute a search, so
/// we statically prevent callers from causing RefCell to panic at runtime
/// due to a borrowing violation.
line_buffer: RefCell<LineBuffer>,
/// A buffer in which to store the contents of a reader when performing a
/// multi line search. In particular, multi line searches cannot be
/// performed incrementally, and need the entire haystack in memory at
/// once.
multi_line_buffer: RefCell<Vec<u8>>,
}
impl Searcher {
/// Create a new searcher with a default configuration.
///
/// To configure the searcher (e.g., invert matching, enable memory maps,
/// enable contexts, etc.), use the [`SearcherBuilder`].
pub fn new() -> Searcher {
SearcherBuilder::new().build()
}
/// Execute a search over the file with the given path and write the
/// results to the given sink.
///
/// If memory maps are enabled and the searcher heuristically believes
/// memory maps will help the search run faster, then this will use
/// memory maps. For this reason, callers should prefer using this method
/// or `search_file` over the more generic `search_reader` when possible.
pub fn search_path<P, M, S>(
&mut self,
matcher: M,
path: P,
write_to: S,
) -> Result<(), S::Error>
where
P: AsRef<Path>,
M: Matcher,
S: Sink,
{
let path = path.as_ref();
let file = File::open(path).map_err(S::Error::error_io)?;
self.search_file_maybe_path(matcher, Some(path), &file, write_to)
}
/// Execute a search over a file and write the results to the given sink.
///
/// If memory maps are enabled and the searcher heuristically believes
/// memory maps will help the search run faster, then this will use
/// memory maps. For this reason, callers should prefer using this method
/// or `search_path` over the more generic `search_reader` when possible.
pub fn search_file<M, S>(
&mut self,
matcher: M,
file: &File,
write_to: S,
) -> Result<(), S::Error>
where
M: Matcher,
S: Sink,
{
self.search_file_maybe_path(matcher, None, file, write_to)
}
fn search_file_maybe_path<M, S>(
&mut self,
matcher: M,
path: Option<&Path>,
file: &File,
write_to: S,
) -> Result<(), S::Error>
where
M: Matcher,
S: Sink,
{
if let Some(mmap) = self.config.mmap.open(file, path) {
log::trace!("{:?}: searching via memory map", path);
return self.search_slice(matcher, &mmap, write_to);
}
// Fast path for multi-line searches of files when memory maps are not
// enabled. This pre-allocates a buffer roughly the size of the file,
// which isn't possible when searching an arbitrary std::io::Read.
if self.multi_line_with_matcher(&matcher) {
log::trace!(
"{:?}: reading entire file on to heap for mulitline",
path
);
self.fill_multi_line_buffer_from_file::<S>(file)?;
log::trace!("{:?}: searching via multiline strategy", path);
MultiLine::new(
self,
matcher,
&*self.multi_line_buffer.borrow(),
write_to,
)
.run()
} else {
log::trace!("{:?}: searching using generic reader", path);
self.search_reader(matcher, file, write_to)
}
}
/// Execute a search over any implementation of `std::io::Read` and write
/// the results to the given sink.
///
/// When possible, this implementation will search the reader incrementally
/// without reading it into memory. In some cases---for example, if multi
/// line search is enabled---an incremental search isn't possible and the
/// given reader is consumed completely and placed on the heap before
/// searching begins. For this reason, when multi line search is enabled,
/// one should try to use higher level APIs (e.g., searching by file or
/// file path) so that memory maps can be used if they are available and
/// enabled.
pub fn search_reader<M, R, S>(
&mut self,
matcher: M,
read_from: R,
write_to: S,
) -> Result<(), S::Error>
where
M: Matcher,
R: io::Read,
S: Sink,
{
self.check_config(&matcher).map_err(S::Error::error_config)?;
let mut decode_buffer = self.decode_buffer.borrow_mut();
let decoder = self
.decode_builder
.build_with_buffer(read_from, &mut *decode_buffer)
.map_err(S::Error::error_io)?;
if self.multi_line_with_matcher(&matcher) {
log::trace!(
"generic reader: reading everything to heap for multiline"
);
self.fill_multi_line_buffer_from_reader::<_, S>(decoder)?;
log::trace!("generic reader: searching via multiline strategy");
MultiLine::new(
self,
matcher,
&*self.multi_line_buffer.borrow(),
write_to,
)
.run()
} else {
let mut line_buffer = self.line_buffer.borrow_mut();
let rdr = LineBufferReader::new(decoder, &mut *line_buffer);
log::trace!("generic reader: searching via roll buffer strategy");
ReadByLine::new(self, matcher, rdr, write_to).run()
}
}
/// Execute a search over the given slice and write the results to the
/// given sink.
pub fn search_slice<M, S>(
&mut self,
matcher: M,
slice: &[u8],
write_to: S,
) -> Result<(), S::Error>
where
M: Matcher,
S: Sink,
{
self.check_config(&matcher).map_err(S::Error::error_config)?;
// We can search the slice directly, unless we need to do transcoding.
if self.slice_needs_transcoding(slice) {
log::trace!(
"slice reader: needs transcoding, using generic reader"
);
return self.search_reader(matcher, slice, write_to);
}
if self.multi_line_with_matcher(&matcher) {
log::trace!("slice reader: searching via multiline strategy");
MultiLine::new(self, matcher, slice, write_to).run()
} else {
log::trace!("slice reader: searching via slice-by-line strategy");
SliceByLine::new(self, matcher, slice, write_to).run()
}
}
/// Set the binary detection method used on this searcher.
pub fn set_binary_detection(&mut self, detection: BinaryDetection) {
self.config.binary = detection.clone();
self.line_buffer.borrow_mut().set_binary_detection(detection.0);
}
/// Check that the searcher's configuration and the matcher are consistent
/// with each other.
fn check_config<M: Matcher>(&self, matcher: M) -> Result<(), ConfigError> {
if self.config.heap_limit == Some(0) && !self.config.mmap.is_enabled()
{
return Err(ConfigError::SearchUnavailable);
}
let matcher_line_term = match matcher.line_terminator() {
None => return Ok(()),
Some(line_term) => line_term,
};
if matcher_line_term != self.config.line_term {
return Err(ConfigError::MismatchedLineTerminators {
matcher: matcher_line_term,
searcher: self.config.line_term,
});
}
Ok(())
}
/// Returns true if and only if the given slice needs to be transcoded.
fn slice_needs_transcoding(&self, slice: &[u8]) -> bool {
self.config.encoding.is_some()
|| (self.config.bom_sniffing && slice_has_bom(slice))
}
}
/// The following methods permit querying the configuration of a searcher.
/// These can be useful in generic implementations of [`Sink`], where the
/// output may be tailored based on how the searcher is configured.
impl Searcher {
/// Returns the line terminator used by this searcher.
#[inline]
pub fn line_terminator(&self) -> LineTerminator {
self.config.line_term
}
/// Returns the type of binary detection configured on this searcher.
#[inline]
pub fn binary_detection(&self) -> &BinaryDetection {
&self.config.binary
}
/// Returns true if and only if this searcher is configured to invert its
/// search results. That is, matching lines are lines that do **not** match
/// the searcher's matcher.
#[inline]
pub fn invert_match(&self) -> bool {
self.config.invert_match
}
/// Returns true if and only if this searcher is configured to count line
/// numbers.
#[inline]
pub fn line_number(&self) -> bool {
self.config.line_number
}
/// Returns true if and only if this searcher is configured to perform
/// multi line search.
#[inline]
pub fn multi_line(&self) -> bool {
self.config.multi_line
}
/// Returns true if and only if this searcher is configured to stop when in
/// finds a non-matching line after a matching one.
#[inline]
pub fn stop_on_nonmatch(&self) -> bool {
self.config.stop_on_nonmatch
}
/// Returns true if and only if this searcher will choose a multi-line
/// strategy given the provided matcher.
///
/// This may diverge from the result of `multi_line` in cases where the
/// searcher has been configured to execute a search that can report
/// matches over multiple lines, but where the matcher guarantees that it
/// will never produce a match over multiple lines.
pub fn multi_line_with_matcher<M: Matcher>(&self, matcher: M) -> bool {
if !self.multi_line() {
return false;
}
if let Some(line_term) = matcher.line_terminator() {
if line_term == self.line_terminator() {
return false;
}
}
if let Some(non_matching) = matcher.non_matching_bytes() {
// If the line terminator is CRLF, we don't actually need to care
// whether the regex can match `\r` or not. Namely, a `\r` is
// neither necessary nor sufficient to terminate a line. A `\n` is
// always required.
if non_matching.contains(self.line_terminator().as_byte()) {
return false;
}
}
true
}
/// Returns the number of "after" context lines to report. When context
/// reporting is not enabled, this returns `0`.
#[inline]
pub fn after_context(&self) -> usize {
self.config.after_context
}
/// Returns the number of "before" context lines to report. When context
/// reporting is not enabled, this returns `0`.
#[inline]
pub fn before_context(&self) -> usize {
self.config.before_context
}
/// Returns true if and only if the searcher has "passthru" mode enabled.
#[inline]
pub fn passthru(&self) -> bool {
self.config.passthru
}
/// Fill the buffer for use with multi-line searching from the given file.
/// This reads from the file until EOF or until an error occurs. If the
/// contents exceed the configured heap limit, then an error is returned.
fn fill_multi_line_buffer_from_file<S: Sink>(
&self,
file: &File,
) -> Result<(), S::Error> {
assert!(self.config.multi_line);
let mut decode_buffer = self.decode_buffer.borrow_mut();
let mut read_from = self
.decode_builder
.build_with_buffer(file, &mut *decode_buffer)
.map_err(S::Error::error_io)?;
// If we don't have a heap limit, then we can defer to std's
// read_to_end implementation. fill_multi_line_buffer_from_reader will
// do this too, but since we have a File, we can be a bit smarter about
// pre-allocating here.
//
// If we're transcoding, then our pre-allocation might not be exact,
// but is probably still better than nothing.
if self.config.heap_limit.is_none() {
let mut buf = self.multi_line_buffer.borrow_mut();
buf.clear();
let cap =
file.metadata().map(|m| m.len() as usize + 1).unwrap_or(0);
buf.reserve(cap);
read_from.read_to_end(&mut *buf).map_err(S::Error::error_io)?;
return Ok(());
}
self.fill_multi_line_buffer_from_reader::<_, S>(read_from)
}
/// Fill the buffer for use with multi-line searching from the given
/// reader. This reads from the reader until EOF or until an error occurs.
/// If the contents exceed the configured heap limit, then an error is
/// returned.
fn fill_multi_line_buffer_from_reader<R: io::Read, S: Sink>(
&self,
mut read_from: R,
) -> Result<(), S::Error> {
assert!(self.config.multi_line);
let mut buf = self.multi_line_buffer.borrow_mut();
buf.clear();
// If we don't have a heap limit, then we can defer to std's
// read_to_end implementation...
let heap_limit = match self.config.heap_limit {
Some(heap_limit) => heap_limit,
None => {
read_from
.read_to_end(&mut *buf)
.map_err(S::Error::error_io)?;
return Ok(());
}
};
if heap_limit == 0 {
return Err(S::Error::error_io(alloc_error(heap_limit)));
}
// ... otherwise we need to roll our own. This is likely quite a bit
// slower than what is optimal, but we avoid worry about memory safety
// until there's a compelling reason to speed this up.
buf.resize(cmp::min(DEFAULT_BUFFER_CAPACITY, heap_limit), 0);
let mut pos = 0;
loop {
let nread = match read_from.read(&mut buf[pos..]) {
Ok(nread) => nread,
Err(ref err) if err.kind() == io::ErrorKind::Interrupted => {
continue;
}
Err(err) => return Err(S::Error::error_io(err)),
};
if nread == 0 {
buf.resize(pos, 0);
return Ok(());
}
pos += nread;
if buf[pos..].is_empty() {
let additional = heap_limit - buf.len();
if additional == 0 {
return Err(S::Error::error_io(alloc_error(heap_limit)));
}
let limit = buf.len() + additional;
let doubled = 2 * buf.len();
buf.resize(cmp::min(doubled, limit), 0);
}
}
}
}
/// Returns true if and only if the given slice begins with a UTF-8 or UTF-16
/// BOM.
///
/// This is used by the searcher to determine if a transcoder is necessary.
/// Otherwise, it is advantageous to search the slice directly.
fn slice_has_bom(slice: &[u8]) -> bool {
let enc = match encoding_rs::Encoding::for_bom(slice) {
None => return false,
Some((enc, _)) => enc,
};
[encoding_rs::UTF_16LE, encoding_rs::UTF_16BE, encoding_rs::UTF_8]
.contains(&enc)
}
#[cfg(test)]
mod tests {
use crate::testutil::{KitchenSink, RegexMatcher};
use super::*;
#[test]
fn config_error_heap_limit() {
let matcher = RegexMatcher::new("");
let sink = KitchenSink::new();
let mut searcher = SearcherBuilder::new().heap_limit(Some(0)).build();
let res = searcher.search_slice(matcher, &[], sink);
assert!(res.is_err());
}
#[test]
fn config_error_line_terminator() {
let mut matcher = RegexMatcher::new("");
matcher.set_line_term(Some(LineTerminator::byte(b'z')));
let sink = KitchenSink::new();
let mut searcher = Searcher::new();
let res = searcher.search_slice(matcher, &[], sink);
assert!(res.is_err());
}
#[test]
fn uft8_bom_sniffing() {
// See: https://github.com/BurntSushi/ripgrep/issues/1638
// ripgrep must sniff utf-8 BOM, just like it does with utf-16
let matcher = RegexMatcher::new("foo");
let haystack: &[u8] = &[0xef, 0xbb, 0xbf, 0x66, 0x6f, 0x6f];
let mut sink = KitchenSink::new();
let mut searcher = SearcherBuilder::new().build();
let res = searcher.search_slice(matcher, haystack, &mut sink);
assert!(res.is_ok());
let sink_output = String::from_utf8(sink.as_bytes().to_vec()).unwrap();
assert_eq!(sink_output, "1:0:foo\nbyte count:3\n");
}
}