Merge pull request #2909 from jfinkels/dd-conv-ascii-unblock

dd: block/unblock on ebcdic/ascii conversions
This commit is contained in:
Sylvestre Ledru 2022-01-25 14:37:20 +01:00 committed by GitHub
commit 630b5d8577
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
3 changed files with 62 additions and 0 deletions

View file

@ -444,6 +444,20 @@ pub fn parse_conv_flag_input(matches: &Matches) -> Result<IConvFlags, ParseError
return Err(ParseError::MultipleFmtTable); return Err(ParseError::MultipleFmtTable);
} else { } else {
fmt = Some(flag); fmt = Some(flag);
// From the GNU documentation:
//
// > ascii
// >
// > Convert EBCDIC to ASCII, using the conversion
// > table specified by POSIX. This provides a 1:1
// > translation for all 256 bytes. This implies
// > conv=unblock; input is converted to ASCII
// > before trailing spaces are deleted.
//
// -- https://www.gnu.org/software/coreutils/manual/html_node/dd-invocation.html
if cbs.is_some() {
iconvflags.unblock = cbs;
}
} }
} }
ConvFlag::FmtAtoE => { ConvFlag::FmtAtoE => {
@ -451,6 +465,19 @@ pub fn parse_conv_flag_input(matches: &Matches) -> Result<IConvFlags, ParseError
return Err(ParseError::MultipleFmtTable); return Err(ParseError::MultipleFmtTable);
} else { } else {
fmt = Some(flag); fmt = Some(flag);
// From the GNU documentation:
//
// > ebcdic
// >
// > Convert ASCII to EBCDIC. This is the inverse
// > of the ascii conversion. This implies
// > conv=block; trailing spaces are added before
// > being converted to EBCDIC.
//
// -- https://www.gnu.org/software/coreutils/manual/html_node/dd-invocation.html
if cbs.is_some() {
iconvflags.block = cbs;
}
} }
} }
ConvFlag::FmtAtoI => { ConvFlag::FmtAtoI => {

View file

@ -157,6 +157,7 @@ fn test_all_top_level_args_no_leading_dashes() {
assert_eq!( assert_eq!(
IConvFlags { IConvFlags {
ctable: Some(&EBCDIC_TO_ASCII_LCASE_TO_UCASE), ctable: Some(&EBCDIC_TO_ASCII_LCASE_TO_UCASE),
unblock: Some(1), // because ascii implies unblock
..IConvFlags::default() ..IConvFlags::default()
}, },
parse_conv_flag_input(&matches).unwrap() parse_conv_flag_input(&matches).unwrap()
@ -241,6 +242,7 @@ fn test_all_top_level_args_with_leading_dashes() {
assert_eq!( assert_eq!(
IConvFlags { IConvFlags {
ctable: Some(&EBCDIC_TO_ASCII_LCASE_TO_UCASE), ctable: Some(&EBCDIC_TO_ASCII_LCASE_TO_UCASE),
unblock: Some(1), // because ascii implies unblock
..IConvFlags::default() ..IConvFlags::default()
}, },
parse_conv_flag_input(&matches).unwrap() parse_conv_flag_input(&matches).unwrap()

View file

@ -559,5 +559,38 @@ fn test_unicode_filenames() {
); );
} }
#[test]
fn test_conv_ascii_implies_unblock() {
// 0x40 = 0o100 = 64, which gets converted to ' '
// 0xc1 = 0o301 = 193, which gets converted to 'A'
//
// `conv=ascii` implies `conv=unblock`, which means trailing paces
// are stripped and a newline is appended at the end of each
// block.
//
// `cbs=4` means use a conversion block size of 4 bytes per block.
new_ucmd!()
.args(&["conv=ascii", "cbs=4"])
.pipe_in(b"\x40\xc1\x40\xc1\x40\xc1\x40\x40".to_vec())
.succeeds()
.stdout_is(" A A\n A\n");
}
#[test]
fn test_conv_ebcdic_implies_block() {
// 0x40 = 0o100 = 64, which is the result of converting from ' '
// 0xc1 = 0o301 = 193, which is the result of converting from 'A'
//
// `conv=ebcdic` implies `conv=block`, which means trailing spaces
// are added to pad each block.
//
// `cbs=4` means use a conversion block size of 4 bytes per block.
new_ucmd!()
.args(&["conv=ebcdic", "cbs=4"])
.pipe_in(" A A\n A\n")
.succeeds()
.stdout_is_bytes(b"\x40\xc1\x40\xc1\x40\xc1\x40\x40");
}
// conv=[ascii,ebcdic,ibm], conv=[ucase,lcase], conv=[block,unblock], conv=sync // conv=[ascii,ebcdic,ibm], conv=[ucase,lcase], conv=[block,unblock], conv=sync
// TODO: Move conv tests from unit test module // TODO: Move conv tests from unit test module