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
|
use std::error;
use std::io::{self, Write};
use std::process;
use std::sync::Mutex;
use std::time::Instant;
use ignore::WalkState;
use args::Args;
use subject::Subject;
#[macro_use]
mod messages;
mod app;
mod args;
mod config;
mod logger;
mod path_printer;
mod search;
mod subject;
// Since Rust no longer uses jemalloc by default, ripgrep will, by default,
// use the system allocator. On Linux, this would normally be glibc's
// allocator, which is pretty good. In particular, ripgrep does not have a
// particularly allocation heavy workload, so there really isn't much
// difference (for ripgrep's purposes) between glibc's allocator and jemalloc.
//
// However, when ripgrep is built with musl, this means ripgrep will use musl's
// allocator, which appears to be substantially worse. (musl's goal is not to
// have the fastest version of everything. Its goal is to be small and amenable
// to static compilation.) Even though ripgrep isn't particularly allocation
// heavy, musl's allocator appears to slow down ripgrep quite a bit. Therefore,
// when building with musl, we use jemalloc.
//
// We don't unconditionally use jemalloc because it can be nice to use the
// system's default allocator by default. Moreover, jemalloc seems to increase
// compilation times by a bit.
//
// Moreover, we only do this on 64-bit systems since jemalloc doesn't support
// i686.
#[cfg(all(target_env = "musl", target_pointer_width = "64"))]
#[global_allocator]
static ALLOC: jemallocator::Jemalloc = jemallocator::Jemalloc;
type Result<T> = ::std::result::Result<T, Box<dyn error::Error>>;
fn main() {
if let Err(err) = Args::parse().and_then(try_main) {
eprintln!("{}", err);
process::exit(2);
}
}
fn try_main(args: Args) -> Result<()> {
use args::Command::*;
let matched = match args.command()? {
Search => search(&args),
SearchParallel => search_parallel(&args),
SearchNever => Ok(false),
Files => files(&args),
FilesParallel => files_parallel(&args),
Types => types(&args),
PCRE2Version => pcre2_version(&args),
}?;
if matched && (args.quiet() || !messages::errored()) {
process::exit(0)
} else if messages::errored() {
process::exit(2)
} else {
process::exit(1)
}
}
/// The top-level entry point for single-threaded search. This recursively
/// steps through the file list (current directory by default) and searches
/// each file sequentially.
fn search(args: &Args) -> Result<bool> {
let started_at = Instant::now();
let quit_after_match = args.quit_after_match()?;
let subject_builder = args.subject_builder();
let mut stats = args.stats()?;
let mut searcher = args.search_worker(args.stdout())?;
let mut matched = false;
for result in args.walker()? {
let subject = match subject_builder.build_from_result(result) {
Some(subject) => subject,
None => continue,
};
let search_result = match searcher.search(&subject) {
Ok(search_result) => search_result,
Err(err) => {
// A broken pipe means graceful termination.
if err.kind() == io::ErrorKind::BrokenPipe {
break;
}
err_message!("{}: {}", subject.path().display(), err);
continue;
}
};
matched = matched || search_result.has_match();
if let Some(ref mut stats) = stats {
*stats += search_result.stats().unwrap();
}
if matched && quit_after_match {
break;
}
}
if let Some(ref stats) = stats {
let elapsed = Instant::now().duration_since(started_at);
// We don't care if we couldn't print this successfully.
let _ = searcher.print_stats(elapsed, stats);
}
Ok(matched)
}
/// The top-level entry point for multi-threaded search. The parallelism is
/// itself achieved by the recursive directory traversal. All we need to do is
/// feed it a worker for performing a search on each file.
fn search_parallel(args: &Args) -> Result<bool> {
use std::sync::atomic::AtomicBool;
use std::sync::atomic::Ordering::SeqCst;
let quit_after_match = args.quit_after_match()?;
let started_at = Instant::now();
let subject_builder = args.subject_builder();
let bufwtr = args.buffer_writer()?;
let stats = args.stats()?.map(Mutex::new);
let matched = AtomicBool::new(false);
let mut searcher_err = None;
args.walker_parallel()?.run(|| {
let bufwtr = &bufwtr;
let stats = &stats;
let matched = &matched;
let subject_builder = &subject_builder;
let mut searcher = match args.search_worker(bufwtr.buffer()) {
Ok(searcher) => searcher,
Err(err) => {
searcher_err = Some(err);
return Box::new(move |_| WalkState::Quit);
}
};
Box::new(move |result| {
let subject = match subject_builder.build_from_result(result) {
Some(subject) => subject,
None => return WalkState::Continue,
};
searcher.printer().get_mut().clear();
let search_result = match searcher.search(&subject) {
Ok(search_result) => search_result,
Err(err) => {
err_message!("{}: {}", subject.path().display(), err);
return WalkState::Continue;
}
};
if search_result.has_match() {
matched.store(true, SeqCst);
}
if let Some(ref locked_stats) = *stats {
let mut stats = locked_stats.lock().unwrap();
*stats += search_result.stats().unwrap();
}
if let Err(err) = bufwtr.print(searcher.printer().get_mut()) {
// A broken pipe means graceful termination.
if err.kind() == io::ErrorKind::BrokenPipe {
return WalkState::Quit;
}
// Otherwise, we continue on our merry way.
err_message!("{}: {}", subject.path().display(), err);
}
if matched.load(SeqCst) && quit_after_match {
WalkState::Quit
} else {
WalkState::Continue
}
})
});
if let Some(err) = searcher_err.take() {
return Err(err);
}
if let Some(ref locked_stats) = stats {
let elapsed = Instant::now().duration_since(started_at);
let stats = locked_stats.lock().unwrap();
let mut searcher = args.search_worker(args.stdout())?;
// We don't care if we couldn't print this successfully.
let _ = searcher.print_stats(elapsed, &stats);
}
Ok(matched.load(SeqCst))
}
/// The top-level entry point for listing files without searching them. This
/// recursively steps through the file list (current directory by default) and
/// prints each path sequentially using a single thread.
fn files(args: &Args) -> Result<bool> {
let quit_after_match = args.quit_after_match()?;
let subject_builder = args.subject_builder();
let mut matched = false;
let mut path_printer = args.path_printer(args.stdout())?;
for result in args.walker()? {
let subject = match subject_builder.build_from_result(result) {
Some(subject) => subject,
None => continue,
};
matched = true;
if quit_after_match {
break;
}
if let Err(err) = path_printer.write_path(subject.path()) {
// A broken pipe means graceful termination.
if err.kind() == io::ErrorKind::BrokenPipe {
break;
}
// Otherwise, we have some other error that's preventing us from
// writing to stdout, so we should bubble it up.
return Err(err.into());
}
}
Ok(matched)
}
/// The top-level entry point for listing files without searching them. This
/// recursively steps through the file list (current directory by default) and
/// prints each path sequentially using multiple threads.
fn files_parallel(args: &Args) -> Result<bool>
|