Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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
29 changes: 20 additions & 9 deletions src/uu/printf/src/printf.rs
Original file line number Diff line number Diff line change
Expand Up @@ -7,7 +7,7 @@ use std::io::stdout;
use std::ops::ControlFlow;
use uucore::error::{UResult, UUsageError};
use uucore::format::{FormatArgument, FormatItem, parse_spec_and_escape};
use uucore::{format_usage, help_about, help_section, help_usage, show_warning};
use uucore::{format_usage, help_about, help_section, help_usage, os_str_as_bytes, show_warning};

const VERSION: &str = "version";
const HELP: &str = "help";
Expand All @@ -19,23 +19,30 @@ mod options {
pub const FORMAT: &str = "FORMAT";
pub const ARGUMENT: &str = "ARGUMENT";
}

#[uucore::main]
pub fn uumain(args: impl uucore::Args) -> UResult<()> {
let matches = uu_app().get_matches_from(args);

let format = matches
.get_one::<String>(options::FORMAT)
.get_one::<std::ffi::OsString>(options::FORMAT)
.ok_or_else(|| UUsageError::new(1, "missing operand"))?;
let format = os_str_as_bytes(format)?;

let values: Vec<_> = match matches.get_many::<String>(options::ARGUMENT) {
Some(s) => s.map(|s| FormatArgument::Unparsed(s.to_string())).collect(),
let values: Vec<_> = match matches.get_many::<std::ffi::OsString>(options::ARGUMENT) {
// FIXME: use os_str_as_bytes once FormatArgument supports Vec<u8>
Some(s) => s
.map(|os_string| {
FormatArgument::Unparsed(std::ffi::OsStr::to_string_lossy(os_string).to_string())
})
.collect(),
None => vec![],
};

let mut format_seen = false;
let mut args = values.iter().peekable();
for item in parse_spec_and_escape(format.as_ref()) {

// Parse and process the format string
for item in parse_spec_and_escape(format) {
if let Ok(FormatItem::Spec(_)) = item {
format_seen = true;
}
Expand All @@ -58,7 +65,7 @@ pub fn uumain(args: impl uucore::Args) -> UResult<()> {
}

while args.peek().is_some() {
for item in parse_spec_and_escape(format.as_ref()) {
for item in parse_spec_and_escape(format) {
match item?.write(stdout(), &mut args)? {
ControlFlow::Continue(()) => {}
ControlFlow::Break(()) => return Ok(()),
Expand Down Expand Up @@ -90,6 +97,10 @@ pub fn uu_app() -> Command {
.help("Print version information")
.action(ArgAction::Version),
)
.arg(Arg::new(options::FORMAT))
.arg(Arg::new(options::ARGUMENT).action(ArgAction::Append))
.arg(Arg::new(options::FORMAT).value_parser(clap::value_parser!(std::ffi::OsString)))
.arg(
Arg::new(options::ARGUMENT)
.action(ArgAction::Append)
.value_parser(clap::value_parser!(std::ffi::OsString)),
)
}
21 changes: 20 additions & 1 deletion src/uucore/src/lib/features/format/argument.rs
Original file line number Diff line number Diff line change
Expand Up @@ -58,7 +58,26 @@ impl<'a, T: Iterator<Item = &'a FormatArgument>> ArgumentIter<'a> for T {
};
match next {
FormatArgument::UnsignedInt(n) => *n,
FormatArgument::Unparsed(s) => extract_value(u64::extended_parse(s), s),
FormatArgument::Unparsed(s) => {
// Check if the string is a character literal enclosed in quotes
if s.starts_with(['"', '\'']) {
// Extract the content between the quotes safely using chars
let mut chars = s.trim_matches(|c| c == '"' || c == '\'').chars();
if let Some(first_char) = chars.next() {
if chars.clone().count() > 0 {
// Emit a warning if there are additional characters
let remaining: String = chars.collect();
show_warning!(
"{}: character(s) following character constant have been ignored",
remaining
);
}
return first_char as u64; // Use only the first character
}
return 0; // Empty quotes
}
extract_value(u64::extended_parse(s), s)
}
_ => 0,
}
}
Expand Down
162 changes: 45 additions & 117 deletions tests/by-util/test_printf.rs
Original file line number Diff line number Diff line change
Expand Up @@ -16,40 +16,6 @@ fn basic_literal() {
.stdout_only("hello world");
}

#[test]
fn escaped_tab() {
new_ucmd!()
.args(&["hello\\t world"])
.succeeds()
.stdout_only("hello\t world");
}

#[test]
fn escaped_newline() {
new_ucmd!()
.args(&["hello\\n world"])
.succeeds()
.stdout_only("hello\n world");
}

#[test]
fn escaped_slash() {
new_ucmd!()
.args(&["hello\\\\ world"])
.succeeds()
.stdout_only("hello\\ world");
}

#[test]
fn unescaped_double_quote() {
new_ucmd!().args(&["\\\""]).succeeds().stdout_only("\"");
}

#[test]
fn escaped_hex() {
new_ucmd!().args(&["\\x41"]).succeeds().stdout_only("A");
}

#[test]
fn test_missing_escaped_hex_value() {
new_ucmd!()
Expand All @@ -58,17 +24,12 @@ fn test_missing_escaped_hex_value() {
.stderr_only("printf: missing hexadecimal number in escape\n");
}

#[test]
fn escaped_octal() {
new_ucmd!().args(&["\\101"]).succeeds().stdout_only("A");
}

#[test]
fn escaped_octal_and_newline() {
new_ucmd!()
.args(&["\\0377\\n"])
.args(&["\\101\\0377\\n"])
.succeeds()
.stdout_only("\x1F7\n");
.stdout_only("A\x1F7\n");
}

#[test]
Expand Down Expand Up @@ -145,38 +106,6 @@ fn escaped_unrecognized() {
new_ucmd!().args(&["c\\d"]).succeeds().stdout_only("c\\d");
}

#[test]
fn sub_string() {
new_ucmd!()
.args(&["hello %s", "world"])
.succeeds()
.stdout_only("hello world");
}

#[test]
fn sub_multi_field() {
new_ucmd!()
.args(&["%s %s", "hello", "world"])
.succeeds()
.stdout_only("hello world");
}

#[test]
fn sub_repeat_format_str() {
new_ucmd!()
.args(&["%s.", "hello", "world"])
.succeeds()
.stdout_only("hello.world.");
}

#[test]
fn sub_string_ignore_escapes() {
new_ucmd!()
.args(&["hello %s", "\\tworld"])
.succeeds()
.stdout_only("hello \\tworld");
}

#[test]
fn sub_b_string_handle_escapes() {
new_ucmd!()
Expand Down Expand Up @@ -705,27 +634,11 @@ fn sub_any_asterisk_second_param_with_integer() {
}

#[test]
fn sub_any_specifiers_no_params() {
new_ucmd!()
.args(&["%ztlhLji", "3"]) //spell-checker:disable-line
.succeeds()
.stdout_only("3");
}

#[test]
fn sub_any_specifiers_after_first_param() {
new_ucmd!()
.args(&["%0ztlhLji", "3"]) //spell-checker:disable-line
.succeeds()
.stdout_only("3");
}

#[test]
fn sub_any_specifiers_after_period() {
new_ucmd!()
.args(&["%0.ztlhLji", "3"]) //spell-checker:disable-line
.succeeds()
.stdout_only("3");
fn sub_any_specifiers() {
// spell-checker:disable-next-line
for format in ["%ztlhLji", "%0ztlhLji", "%0.ztlhLji"] {
new_ucmd!().args(&[format, "3"]).succeeds().stdout_only("3");
}
}

#[test]
Expand Down Expand Up @@ -1027,33 +940,23 @@ fn pad_string() {
}

#[test]
fn format_spec_zero_char_fails() {
// It is invalid to have the format spec '%0c'
new_ucmd!().args(&["%0c", "3"]).fails_with_code(1);
}

#[test]
fn format_spec_zero_string_fails() {
// It is invalid to have the format spec '%0s'
new_ucmd!().args(&["%0s", "3"]).fails_with_code(1);
}

#[test]
fn invalid_precision_fails() {
// It is invalid to have length of output string greater than i32::MAX
new_ucmd!()
.args(&["%.*d", "2147483648", "0"])
.fails()
.stderr_is("printf: invalid precision: '2147483648'\n");
fn format_spec_zero_fails() {
// It is invalid to have the format spec
for format in ["%0c", "%0s"] {
new_ucmd!().args(&[format, "3"]).fails_with_code(1);
}
}

#[test]
fn float_invalid_precision_fails() {
fn invalid_precision_tests() {
// It is invalid to have length of output string greater than i32::MAX
new_ucmd!()
.args(&["%.*f", "2147483648", "0"])
.fails()
.stderr_is("printf: invalid precision: '2147483648'\n");
for format in ["%.*d", "%.*f"] {
let expected_error = "printf: invalid precision: '2147483648'\n";
new_ucmd!()
.args(&[format, "2147483648", "0"])
.fails()
.stderr_is(expected_error);
}
}

// The following padding-tests test for the cases in which flags in ['0', ' '] are given.
Expand Down Expand Up @@ -1385,3 +1288,28 @@ fn float_arg_with_whitespace() {
.fails()
.stderr_contains("expected a numeric value");
}

#[test]
fn mb_input() {
for format in ["\"á", "\'á", "'\u{e1}"] {
new_ucmd!()
.args(&["%04x\n", format])
.succeeds()
.stdout_only("00e1\n");
}

let cases = vec![
("\"á=", "="),
("\'á-", "-"),
("\'á=-==", "=-=="),
("'\u{e1}++", "++"),
];

for (format, expected) in cases {
new_ucmd!()
.args(&["%04x\n", format])
.succeeds()
.stdout_is("00e1\n")
.stderr_is(format!("printf: warning: {expected}: character(s) following character constant have been ignored\n"));
}
}
Loading