mirror of
https://github.com/RGBCube/uutils-coreutils
synced 2025-07-28 11:37:44 +00:00
Merge pull request #1495 from orottier/wc
wc: Do not decode UTF8 when only counting bytes/newlines
This commit is contained in:
commit
06fe387c76
1 changed files with 21 additions and 16 deletions
|
@ -146,6 +146,9 @@ fn wc(files: Vec<String>, settings: &Settings) -> StdResult<(), i32> {
|
||||||
let mut results = vec![];
|
let mut results = vec![];
|
||||||
let mut max_width: usize = 0;
|
let mut max_width: usize = 0;
|
||||||
|
|
||||||
|
// we do not need to decode the byte stream if we're only counting bytes/newlines
|
||||||
|
let decode_chars = settings.show_chars || settings.show_words || settings.show_max_line_length;
|
||||||
|
|
||||||
for path in &files {
|
for path in &files {
|
||||||
let mut reader = open(&path[..])?;
|
let mut reader = open(&path[..])?;
|
||||||
|
|
||||||
|
@ -173,6 +176,7 @@ fn wc(files: Vec<String>, settings: &Settings) -> StdResult<(), i32> {
|
||||||
|
|
||||||
byte_count += raw_line.len();
|
byte_count += raw_line.len();
|
||||||
|
|
||||||
|
if decode_chars {
|
||||||
// try and convert the bytes to UTF-8 first
|
// try and convert the bytes to UTF-8 first
|
||||||
let current_char_count;
|
let current_char_count;
|
||||||
match from_utf8(&raw_line[..]) {
|
match from_utf8(&raw_line[..]) {
|
||||||
|
@ -192,6 +196,7 @@ fn wc(files: Vec<String>, settings: &Settings) -> StdResult<(), i32> {
|
||||||
// matches GNU 'wc' behaviour
|
// matches GNU 'wc' behaviour
|
||||||
longest_line_length = current_char_count - 1;
|
longest_line_length = current_char_count - 1;
|
||||||
}
|
}
|
||||||
|
}
|
||||||
|
|
||||||
raw_line.truncate(0);
|
raw_line.truncate(0);
|
||||||
}
|
}
|
||||||
|
|
Loading…
Add table
Add a link
Reference in a new issue