Skip to content

Miscellaneous improvements #15

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

Open
AaronErhardt wants to merge 3 commits into
base: master
Choose a base branch
from
Open

Miscellaneous improvements #15

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
b344f21
Minor improvements
AaronErhardt Aug 18, 2022
1f340ea
Simplifications and cleanups
AaronErhardt Aug 18, 2022
1f0def7
Update to 2021 edition
AaronErhardt Aug 18, 2022
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
9 changes: 2 additions & 7 deletions Cargo.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,18 +1,13 @@
[package]
name = "shell-words"
version = "1.1.0"
edition = "2021"
authors = ["Tomasz Miąsko <tomasz.miasko@gmail.com>"]
license = "MIT/Apache-2.0"
repository = "https://github.com/tmiasko/shell-words"
description = "Process command line according to parsing rules of UNIX shell"
readme = "README.md"
keywords = [
"quote",
"shell",
"split",
"unix",
"words",
]
keywords = ["quote", "shell", "split", "unix", "words"]

[features]
default = ["std"]
Expand Down
216 changes: 98 additions & 118 deletions src/lib.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,7 +8,6 @@
//!
//! [posix-shell]: http://pubs.opengroup.org/onlinepubs/9699919799/utilities/V3_chap02.html

#![cfg_attr(not(feature = "std"), no_std)]
#![forbid(unsafe_code)]

#[cfg(feature = "std")]
Expand Down Expand Up @@ -84,8 +83,8 @@ enum State {
///
/// # Compatibility with other implementations
///
/// It should be fully compatible with g_shell_parse_argv from GLib, except that
/// in GLib it is an error not to have any words after tokenization.
/// It should be fully compatible with `g_shell_parse_argv` from GLib, except
/// that in GLib it is an error not to have any words after tokenization.
///
/// It is also very close to shlex.split available in Python standard library,
/// when used in POSIX mode with support for comments. Though, shlex
Expand Down Expand Up @@ -132,96 +131,99 @@ pub fn split(s: &str) -> Result<Vec<String>, ParseError> {
let mut state = Delimiter;

loop {
let c = chars.next();
state = match state {
Delimiter => match c {
None => break,
Some('\'') => SingleQuoted,
Some('\"') => DoubleQuoted,
Some('\\') => Backslash,
Some('\t') | Some(' ') | Some('\n') => Delimiter,
Some('#') => Comment,
Some(c) => {
word.push(c);
Unquoted
}
},
Backslash => match c {
None => {
state = if let Some(c) = chars.next() {
// Process new character
match state {
Delimiter => match c {
'\'' => SingleQuoted,
'\"' => DoubleQuoted,
'\\' => Backslash,
'\t' | ' ' | '\n' => Delimiter,
'#' => Comment,
c => {
word.push(c);
Unquoted
}
},
Backslash => match c {
'\n' => Delimiter,
c => {
word.push(c);
Unquoted
}
},
Unquoted => match c {
'\'' => SingleQuoted,
'\"' => DoubleQuoted,
'\\' => UnquotedBackslash,
'\t' | ' ' | '\n' => {
words.push(mem::take(&mut word));
Delimiter
}
c => {
word.push(c);
Unquoted
}
},
UnquotedBackslash => match c {
'\n' => Unquoted,
c => {
word.push(c);
Unquoted
}
},
SingleQuoted => match c {
'\'' => Unquoted,
c => {
word.push(c);
SingleQuoted
}
},
DoubleQuoted => match c {
'\"' => Unquoted,
'\\' => DoubleQuotedBackslash,
c => {
word.push(c);
DoubleQuoted
}
},
DoubleQuotedBackslash => match c {
'\n' => DoubleQuoted,
'$' | '`' | '"' | '\\' => {
word.push(c);
DoubleQuoted
}
c => {
word.push('\\');
word.push(c);
DoubleQuoted
}
},
Comment => match c {
'\n' => Delimiter,
_ => Comment,
},
}
} else {
// Process end of input
match state {
Delimiter | Comment => break,
Backslash => {
word.push('\\');
words.push(mem::replace(&mut word, String::new()));
words.push(mem::take(&mut word));
break;
}
Some('\n') => Delimiter,
Some(c) => {
word.push(c);
Unquoted
}
},
Unquoted => match c {
None => {
words.push(mem::replace(&mut word, String::new()));
Unquoted => {
words.push(mem::take(&mut word));
break;
}
Some('\'') => SingleQuoted,
Some('\"') => DoubleQuoted,
Some('\\') => UnquotedBackslash,
Some('\t') | Some(' ') | Some('\n') => {
words.push(mem::replace(&mut word, String::new()));
Delimiter
}
Some(c) => {
word.push(c);
Unquoted
}
},
UnquotedBackslash => match c {
None => {
UnquotedBackslash => {
word.push('\\');
words.push(mem::replace(&mut word, String::new()));
words.push(mem::take(&mut word));
break;
}
Some('\n') => Unquoted,
Some(c) => {
word.push(c);
Unquoted
}
},
SingleQuoted => match c {
None => return Err(ParseError),
Some('\'') => Unquoted,
Some(c) => {
word.push(c);
SingleQuoted
}
},
DoubleQuoted => match c {
None => return Err(ParseError),
Some('\"') => Unquoted,
Some('\\') => DoubleQuotedBackslash,
Some(c) => {
word.push(c);
DoubleQuoted
}
},
DoubleQuotedBackslash => match c {
None => return Err(ParseError),
Some('\n') => DoubleQuoted,
Some(c @ '$') | Some(c @ '`') | Some(c @ '"') | Some(c @ '\\') => {
word.push(c);
DoubleQuoted
}
Some(c) => {
word.push('\\');
word.push(c);
DoubleQuoted
}
},
Comment => match c {
None => break,
Some('\n') => Delimiter,
Some(_) => Comment,
},
SingleQuoted | DoubleQuoted | DoubleQuotedBackslash => return Err(ParseError),
}
}
}

Expand All @@ -244,33 +246,24 @@ fn escape_style(s: &str) -> EscapeStyle {
}

let mut special = false;
let mut newline = false;
let mut single_quote = false;

for c in s.chars() {
match c {
'\n' => {
newline = true;
special = true;
}
'\'' => {
single_quote = true;
special = true;
return EscapeStyle::Mixed;
}
'|' | '&' | ';' | '<' | '>' | '(' | ')' | '$' | '`' | '\\' | '"' | ' ' | '\t' | '*'
| '?' | '[' | '#' | '˜' | '=' | '%' => {
'\n' | '|' | '&' | ';' | '<' | '>' | '(' | ')' | '$' | '`' | '\\' | '"' | ' '
| '\t' | '*' | '?' | '[' | '#' | '˜' | '=' | '%' => {
special = true;
}
_ => continue,
}
}

if !special {
EscapeStyle::None
} else if newline && !single_quote {
if special {
EscapeStyle::SingleQuoted
} else {
EscapeStyle::Mixed
EscapeStyle::None
}
}

Expand All @@ -279,25 +272,14 @@ fn escape_style(s: &str) -> EscapeStyle {
///
/// It tries to avoid introducing any unnecessary quotes or escape characters,
/// but specifics regarding quoting style are left unspecified.
#[must_use]
pub fn quote(s: &str) -> Cow<str> {
// We are going somewhat out of the way to provide
// minimal amount of quoting in typical cases.
match escape_style(s) {
EscapeStyle::None => s.into(),
EscapeStyle::SingleQuoted => format!("'{}'", s).into(),
EscapeStyle::Mixed => {
let mut quoted = String::new();
quoted.push('\'');
for c in s.chars() {
if c == '\'' {
quoted.push_str("'\\''");
} else {
quoted.push(c);
}
}
quoted.push('\'');
quoted.into()
}
EscapeStyle::Mixed => format!("'{}'", s.replace('\'', "'\\''")).into(),
}
}

Expand Down Expand Up @@ -336,12 +318,10 @@ where
I: IntoIterator<Item = S>,
S: AsRef<str>,
{
let mut line = words.into_iter().fold(String::new(), |mut line, word| {
let quoted = quote(word.as_ref());
line.push_str(quoted.as_ref());
line.push(' ');
line
});
let mut line: String = words
.into_iter()
.map(|word| format!("{} ", quote(word.as_ref())))
.collect();
line.pop();
line
}
Expand Down