twin/ripgrep
1
0
Fork 0
mirror of https://github.com/BurntSushi/ripgrep.git synced 2025-08-09 00:22:00 -07:00
Code Issues Packages Projects Releases Wiki Activity

Move all gitignore matching to separate crate.

Browse Source 
This PR introduces a new sub-crate, `ignore`, which primarily provides a
fast recursive directory iterator that respects ignore files like
gitignore and other configurable filtering rules based on globs or even
file types.

This results in a substantial source of complexity moved out of ripgrep's
core and into a reusable component that others can now (hopefully)
benefit from.

While much of the ignore code carried over from ripgrep's core, a
substantial portion of it was rewritten with the following goals in
mind:

1. Reuse matchers built from gitignore files across directory iteration.
2. Design the matcher data structure to be amenable for parallelizing
   directory iteration. (Indeed, writing the parallel iterator is the
   next step.)

Fixes #9, #44, #45
This commit is contained in:
Andrew Gallant
2016-10-11 19:57:09 -04:00
parent 12b2b1f624
commit d79add341b
30 changed files with 3765 additions and 1760 deletions
Download Patch File Download Diff File Expand all files Collapse all files

78
src/pathutil.rs
View File

@@ -8,7 +8,6 @@ with the raw bytes directly.
On large repositories (like chromium), this can have a ~25% performance
improvement on just listing the files to search (!).
*/
use std::ffi::OsStr;
use std::path::Path;
/// Strip `prefix` from the `path` and return the remainder.
@@ -19,6 +18,7 @@ pub fn strip_prefix<'a, P: AsRef<Path> + ?Sized>(
prefix: &'a P,
path: &'a Path,
) -> Option<&'a Path> {
use std::ffi::OsStr;
use std::os::unix::ffi::OsStrExt;
let prefix = prefix.as_ref().as_os_str().as_bytes();
@@ -40,79 +40,3 @@ pub fn strip_prefix<'a, P: AsRef<Path> + ?Sized>(
) -> Option<&'a Path> {
path.strip_prefix(prefix).ok()
}
/// The final component of the path, if it is a normal file.
///
/// If the path terminates in ., .., or consists solely of a root of prefix,
/// file_name will return None.
#[cfg(unix)]
pub fn file_name<'a, P: AsRef<Path> + ?Sized>(
path: &'a P,
) -> Option<&'a OsStr> {
use std::os::unix::ffi::OsStrExt;
use memchr::memrchr;
let path = path.as_ref().as_os_str().as_bytes();
if path.is_empty() {
return None;
} else if path.len() == 1 && path[0] == b'.' {
return None;
} else if path.last() == Some(&b'.') {
return None;
} else if path.len() >= 2 && &path[path.len() - 2..] == &b".."[..] {
return None;
}
let last_slash = memrchr(b'/', path).map(|i| i + 1).unwrap_or(0);
Some(OsStr::from_bytes(&path[last_slash..]))
}
/// The final component of the path, if it is a normal file.
///
/// If the path terminates in ., .., or consists solely of a root of prefix,
/// file_name will return None.
#[cfg(not(unix))]
pub fn file_name<'a, P: AsRef<Path> + ?Sized>(
path: &'a P,
) -> Option<&'a OsStr> {
path.as_ref().file_name()
}
/// Returns true if and only if this file path is considered to be hidden.
#[cfg(unix)]
pub fn is_hidden<P: AsRef<Path>>(path: P) -> bool {
use std::os::unix::ffi::OsStrExt;
if let Some(name) = file_name(path.as_ref()) {
name.as_bytes().get(0) == Some(&b'.')
} else {
false
}
}
/// Returns true if and only if this file path is considered to be hidden.
#[cfg(not(unix))]
pub fn is_hidden<P: AsRef<Path>>(path: P) -> bool {
if let Some(name) = file_name(path.as_ref()) {
name.to_str().map(|s| s.starts_with(".")).unwrap_or(false)
} else {
false
}
}
/// Returns true if this file path is just a file name. i.e., Its parent is
/// the empty string.
#[cfg(unix)]
pub fn is_file_name<P: AsRef<Path>>(path: P) -> bool {
use std::os::unix::ffi::OsStrExt;
use memchr::memchr;
let path = path.as_ref().as_os_str().as_bytes();
memchr(b'/', path).is_none()
}
/// Returns true if this file path is just a file name. i.e., Its parent is
/// the empty string.
#[cfg(not(unix))]
pub fn is_file_name<P: AsRef<Path>>(path: P) -> bool {
path.as_ref().parent().map(|p| p.as_os_str().is_empty()).unwrap_or(false)
}