rust/ripgrep
1
0
Fork 0
mirror of https://github.com/BurntSushi/ripgrep.git synced 2025-03-17 20:28:03 +02:00
Code Issues Releases Activity

core: dedup patterns

Browse Source 
ripgrep does not, and likely never will, report which pattern matched.
Because of that, we can dedup the patterns via just their concrete
syntax without any fuss.

This is somewhat of a pathological case because you don't expect the end
user to pass duplicate patterns in general. But if the end user
generated a list of, say, names and did not dedup them, then ripgrep
could end up spending a lot of extra time on those duplicates if there
are many of them. By deduping them explicitly in the application, we
essentially remove their extra cost completely.
This commit is contained in:
Andrew Gallant 2023-09-30 08:17:54 -04:00
parent 9c6732bd26
commit 88524a2b52
1 changed files with 22 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

34
crates/core/args.rs
View File

@ -1,4 +1,5 @@
use std::{
collections::HashSet,
env,
ffi::{OsStr, OsString},
io::{self, IsTerminal, Write},
@ -1436,35 +1437,44 @@ impl ArgMatches {
if self.is_present("files") || self.is_present("type-list") {
return Ok(vec![]);
}
let mut seen = HashSet::new();
let mut pats = vec![];
let mut add = |pat: String| {
if !seen.contains(&pat) {
seen.insert(pat.clone());
pats.push(pat);
}
};
match self.values_of_os("regexp") {
None => {
if self.values_of_os("file").is_none() {
if let Some(os_pat) = self.value_of_os("pattern") {
pats.push(self.pattern_from_os_str(os_pat)?);
add(self.pattern_from_os_str(os_pat)?);
}
}
}
Some(os_pats) => {
for os_pat in os_pats {
pats.push(self.pattern_from_os_str(os_pat)?);
add(self.pattern_from_os_str(os_pat)?);
}
}
}
if let Some(paths) = self.values_of_os("file") {
for path in paths {
if path == "-" {
pats.extend(
cli::patterns_from_stdin()?
.into_iter()
.map(|p| self.pattern_from_string(p)),
);
let it = cli::patterns_from_stdin()?
.into_iter()
.map(|p| self.pattern_from_string(p));
for pat in it {
add(pat);
}
} else {
pats.extend(
cli::patterns_from_path(path)?
.into_iter()
.map(|p| self.pattern_from_string(p)),
);
let it = cli::patterns_from_path(path)?
.into_iter()
.map(|p| self.pattern_from_string(p));
for pat in it {
add(pat);
}
}
}
}