Directory Traversal - Rust Cookbook (original) (raw)

Rust Cookbook

Directory Traversal

File names that have been modified in the last 24 hours

Gets the current working directory by calling env::current_dir, then for each entries in fs::read_dir, extracts theDirEntry::path and gets the metadata via fs::Metadata. TheMetadata::modified returns the SystemTime::elapsed time since last modification. Duration::as_secs converts the time to seconds and compared with 24 hours (24 * 60 * 60 seconds). Metadata::is_file filters out directories.

use error_chain::error_chain;

use std::{env, fs};

error_chain! {
    foreign_links {
        Io(std::io::Error);
        SystemTimeError(std::time::SystemTimeError);
    }
}

fn main() -> Result<()> {
    let current_dir = env::current_dir()?;
    println!(
        "Entries modified in the last 24 hours in {:?}:",
        current_dir
    );

    for entry in fs::read_dir(current_dir)? {
        let entry = entry?;
        let path = entry.path();

        let metadata = fs::metadata(&path)?;
        let last_modified = metadata.modified()?.elapsed()?.as_secs();

        if last_modified < 24 * 3600 && metadata.is_file() {
            println!(
                "Last modified: {:?} seconds, is read only: {:?}, size: {:?} bytes, filename: {:?}",
                last_modified,
                metadata.permissions().readonly(),
                metadata.len(),
                path.file_name().ok_or("No filename")?
            );
        }
    }

    Ok(())
}

Find loops for a given path

Use same_file::is_same_file to detect loops for a given path. For example, a loop could be created on a Unix system via symlinks:

mkdir -p /tmp/foo/bar/baz
ln -s /tmp/foo/  /tmp/foo/bar/baz/qux

The following would assert that a loop exists.

use std::io;
use std::path::{Path, PathBuf};
use same_file::is_same_file;

fn contains_loop<P: AsRef<Path>>(path: P) -> io::Result<Option<(PathBuf, PathBuf)>> {
    let path = path.as_ref();
    let mut path_buf = path.to_path_buf();
    while path_buf.pop() {
        if is_same_file(&path_buf, path)? {
            return Ok(Some((path_buf, path.to_path_buf())));
        } else if let Some(looped_paths) = contains_loop(&path_buf)? {
            return Ok(Some(looped_paths));
        }
    }
    return Ok(None);
}

fn main() {
    assert_eq!(
        contains_loop("/tmp/foo/bar/baz/qux/bar/baz").unwrap(),
        Some((
            PathBuf::from("/tmp/foo"),
            PathBuf::from("/tmp/foo/bar/baz/qux")
        ))
    );
}

Recursively find duplicate file names

Find recursively in the current directory duplicate filenames, printing them only once.

use std::collections::HashMap;
use walkdir::WalkDir;

fn main() {
    let mut filenames = HashMap::new();

    for entry in WalkDir::new(".")
            .into_iter()
            .filter_map(Result::ok)
            .filter(|e| !e.file_type().is_dir()) {
        let f_name = String::from(entry.file_name().to_string_lossy());
        let counter = filenames.entry(f_name.clone()).or_insert(0);
        *counter += 1;

        if *counter == 2 {
            println!("{}", f_name);
        }
    }
}

Recursively find all files with given predicate

Find JSON files modified within the last day in the current directory. Using follow_links ensures symbolic links are followed like they were normal directories and files.

use error_chain::error_chain;

use walkdir::WalkDir;

error_chain! {
    foreign_links {
        WalkDir(walkdir::Error);
        Io(std::io::Error);
        SystemTime(std::time::SystemTimeError);
    }
}

fn main() -> Result<()> {
    for entry in WalkDir::new(".")
            .follow_links(true)
            .into_iter()
            .filter_map(|e| e.ok()) {
        let f_name = entry.file_name().to_string_lossy();
        let sec = entry.metadata()?.modified()?;

        if f_name.ends_with(".json") && sec.elapsed()?.as_secs() < 86400 {
            println!("{}", f_name);
        }
    }

    Ok(())
}

Traverse directories while skipping dotfiles

Uses filter_entry to descend recursively into entries passing theis_not_hidden predicate thus skipping hidden files and directories.Iterator::filter applies to each WalkDir::DirEntry even if the parent is a hidden directory.

Root dir "." yields through WalkDir::depth usage in is_not_hiddenpredicate.

use walkdir::{DirEntry, WalkDir};

fn is_not_hidden(entry: &DirEntry) -> bool {
    entry
         .file_name()
         .to_str()
         .map(|s| entry.depth() == 0 || !s.starts_with("."))
         .unwrap_or(false)
}

fn main() {
    WalkDir::new(".")
        .into_iter()
        .filter_entry(|e| is_not_hidden(e))
        .filter_map(|v| v.ok())
        .for_each(|x| println!("{}", x.path().display()));
}

Recursively calculate file sizes at given depth

Recursion depth can be flexibly set by WalkDir::min_depth & WalkDir::max_depth methods. Calculates sum of all file sizes to 3 subfolders depth, ignoring files in the root folder.

use walkdir::WalkDir;

fn main() {
    let total_size = WalkDir::new(".")
        .min_depth(1)
        .max_depth(3)
        .into_iter()
        .filter_map(|entry| entry.ok())
        .filter_map(|entry| entry.metadata().ok())
        .filter(|metadata| metadata.is_file())
        .fold(0, |acc, m| acc + m.len());

    println!("Total size: {} bytes.", total_size);
}

Find all png files recursively

Recursively find all PNG files in the current directory. In this case, the ** pattern matches the current directory and all subdirectories.

Use the ** pattern in any path portion. For example, /media/**/*.pngmatches all PNGs in media and it's subdirectories.

use error_chain::error_chain;

use glob::glob;

error_chain! {
    foreign_links {
        Glob(glob::GlobError);
        Pattern(glob::PatternError);
    }
}

fn main() -> Result<()> {
    for entry in glob("**/*.png")? {
        println!("{}", entry?.display());
    }

    Ok(())
}

Find all files with given pattern ignoring filename case.

Find all image files in the /media/ directory matching the img_[0-9]*.png pattern.

A custom MatchOptions struct is passed to the glob_with function making the glob pattern case insensitive while keeping the other options Default.

use error_chain::error_chain;
use glob::{glob_with, MatchOptions};

error_chain! {
    foreign_links {
        Glob(glob::GlobError);
        Pattern(glob::PatternError);
    }
}

fn main() -> Result<()> {
    let options = MatchOptions {
        case_sensitive: false,
        ..Default::default()
    };

    for entry in glob_with("/media/img_[0-9]*.png", options)? {
        println!("{}", entry?.display());
    }

    Ok(())
}