Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Improve wc #243

Merged
merged 2 commits into from
Sep 23, 2024
Merged

Improve wc #243

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
a855a77
faster wc bytes
guicanat Sep 23, 2024
4d61894
use const table
gcanat Sep 23, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
53 changes: 26 additions & 27 deletions text/wc.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -42,6 +42,7 @@ struct CountInfo {
words: usize,
chars: usize,
nl: usize,
was_space: bool,
}

impl CountInfo {
Expand All @@ -50,6 +51,7 @@ impl CountInfo {
words: 0,
chars: 0,
nl: 0,
was_space: true,
}
}

Expand All @@ -60,6 +62,19 @@ impl CountInfo {
}
}

const fn create_table() -> [bool; 256] {
let mut table = [false; 256];
table[9] = true;
table[10] = true;
table[11] = true;
table[12] = true;
table[13] = true;
table[32] = true;
table
}

const BYTE_TABLE: [bool; 256] = create_table();

fn build_display_str(args: &Args, count: &CountInfo, filename: &OsStr) -> String {
let mut output = String::with_capacity(filename.len() + (3 * 10));

Expand Down Expand Up @@ -109,11 +124,11 @@ fn build_display_str(args: &Args, count: &CountInfo, filename: &OsStr) -> String
output
}

fn wc_file_bytes(count: &mut CountInfo, pathname: &PathBuf) -> io::Result<()> {
fn wc_file_bytes(count: &mut CountInfo, pathname: &PathBuf, table: &[bool; 256]) -> io::Result<()> {
let mut file = plib::io::input_stream(pathname, false)?;

let mut buffer = [0; plib::BUFSZ];
let mut in_word = false;
let mut was_space = count.was_space;

loop {
let n_read = file.read(&mut buffer[..])?;
Expand All @@ -126,30 +141,13 @@ fn wc_file_bytes(count: &mut CountInfo, pathname: &PathBuf) -> io::Result<()> {
let bufslice = &buffer[0..n_read];

for ch_u8 in bufslice {
let ch = *ch_u8 as char;

if ch == '\n' {
count.nl = count.nl + 1;
if in_word {
in_word = false;
count.words = count.words + 1;
}
} else if ch.is_whitespace() {
if in_word {
in_word = false;
count.words = count.words + 1;
}
} else {
if !in_word {
in_word = true;
}
}
let is_space = table[*ch_u8 as usize];
count.nl += (ch_u8 == &10) as usize;
count.words += (!is_space && was_space) as usize;
was_space = is_space;
}
}

if in_word {
count.words = count.words + 1;
}
count.was_space = was_space;

Ok(())
}
Expand Down Expand Up @@ -196,11 +194,12 @@ fn wc_file(
chars_mode: bool,
pathname: &PathBuf,
count: &mut CountInfo,
table: &[bool; 256],
) -> io::Result<()> {
if chars_mode {
wc_file_chars(args, count, pathname)?;
} else {
wc_file_bytes(count, pathname)?;
wc_file_bytes(count, pathname, table)?;
}

let output = build_display_str(args, count, pathname.as_os_str());
Expand Down Expand Up @@ -237,7 +236,7 @@ fn main() -> Result<(), Box<dyn std::error::Error>> {
if args.files.is_empty() {
let mut count = CountInfo::new();

if let Err(e) = wc_file(&args, chars_mode, &PathBuf::new(), &mut count) {
if let Err(e) = wc_file(&args, chars_mode, &PathBuf::new(), &mut count, &BYTE_TABLE) {
exit_code = 1;
eprintln!("stdin: {}", e);
}
Expand All @@ -247,7 +246,7 @@ fn main() -> Result<(), Box<dyn std::error::Error>> {
for filename in &args.files {
let mut count = CountInfo::new();

if let Err(e) = wc_file(&args, chars_mode, filename, &mut count) {
if let Err(e) = wc_file(&args, chars_mode, filename, &mut count, &BYTE_TABLE) {
exit_code = 1;
eprintln!("{}: {}", filename.display(), e);
}
Expand Down