cut.pl: adjust to our messages as they are better (#6921)

* cut.pl: adjust to our messages as they are better

but we still have some differences on this test

* cut: add some missing line return when needed

* cut: add failing tests covered by cut.pl

* Remove dup test

* cut: add spell-checker:ignore line to test

---------

Co-authored-by: Daniel Hofstetter <[email protected]>

Author: sylvestre

.vscode/cspell.dictionaries/jargon.wordlist.txt

@@ -157,6 +157,8 @@ retval
 subdir
 val
 vals
+inval
+nofield
 
 # * clippy
 uninlined

src/uu/cut/src/cut.rs

@@ -131,8 +131,9 @@ fn cut_fields_explicit_out_delim<R: Read, M: Matcher>(
 
         if delim_search.peek().is_none() {
             if !only_delimited {
+                // Always write the entire line, even if it doesn't end with `newline_char`
                 out.write_all(line)?;
-                if line[line.len() - 1] != newline_char {
+                if line.is_empty() || line[line.len() - 1] != newline_char {
                     out.write_all(&[newline_char])?;
                 }
             }
@@ -213,8 +214,12 @@ fn cut_fields_implicit_out_delim<R: Read, M: Matcher>(
         let mut print_delim = false;
 
         if delim_search.peek().is_none() {
-            if !only_delimited && line[line.len() - 1] == newline_char {
+            if !only_delimited {
+                // Always write the entire line, even if it doesn't end with `newline_char`
                 out.write_all(line)?;
+                if line.is_empty() || line[line.len() - 1] != newline_char {
+                    out.write_all(&[newline_char])?;
+                }
             }
 
             return Ok(true);

tests/by-util/test_cut.rs

@@ -2,6 +2,9 @@
 //
 // For the full copyright and license information, please view the LICENSE
 // file that was distributed with this source code.
+
+// spell-checker:ignore defg
+
 use crate::common::util::TestScenario;
 
 static INPUT: &str = "lists.txt";
@@ -288,7 +291,7 @@ fn test_newline_delimited() {
         .args(&["-f", "1", "-d", "\n"])
         .pipe_in("a:1\nb:")
         .succeeds()
-        .stdout_only_bytes("a:1\n");
+        .stdout_only_bytes("a:1\nb:\n");
 }
 
 #[test]
@@ -329,3 +332,31 @@ fn test_8bit_non_utf8_delimiter() {
         .succeeds()
         .stdout_check(|out| out == "b_c\n".as_bytes());
 }
+
+#[test]
+fn test_newline_preservation_with_f1_option() {
+    let (at, mut ucmd) = at_and_ucmd!();
+    at.write("1", "a\nb");
+    let expected = "a\nb\n";
+    ucmd.args(&["-f1-", "1"]).succeeds().stdout_is(expected);
+}
+
+#[ignore = "Not yet implemented"]
+#[test]
+fn test_output_delimiter_with_character_ranges() {
+    new_ucmd!()
+        .args(&["-c2-3,4-", "--output-delim=:"])
+        .pipe_in("abcdefg\n")
+        .succeeds()
+        .stdout_only("bc:defg\n");
+}
+
+#[ignore = "Not yet implemented"]
+#[test]
+fn test_output_delimiter_with_adjacent_ranges() {
+    new_ucmd!()
+        .args(&["-b1-2,3-4", "--output-d=:"])
+        .pipe_in("abcd\n")
+        .succeeds()
+        .stdout_only("ab:cd\n");
+}

util/gnu-patches/tests_cut_error_msg.patch

@@ -0,0 +1,72 @@
+diff --git a/tests/cut/cut.pl b/tests/cut/cut.pl
+index 1670db02e..ed633792a 100755
+--- a/tests/cut/cut.pl
++++ b/tests/cut/cut.pl
+@@ -29,13 +29,15 @@ my $mb_locale = $ENV{LOCALE_FR_UTF8};
+ 
+ my $prog = 'cut';
+ my $try = "Try '$prog --help' for more information.\n";
+-my $from_field1 = "$prog: fields are numbered from 1\n$try";
+-my $from_pos1 =   "$prog: byte/character positions are numbered from 1\n$try";
+-my $inval_fld = "$prog: invalid field range\n$try";
+-my $inval_pos = "$prog: invalid byte or character range\n$try";
+-my $no_endpoint = "$prog: invalid range with no endpoint: -\n$try";
+-my $nofield = "$prog: an input delimiter may be specified only when " .
+-              "operating on fields\n$try";
++my $from_field1 = "$prog: range '' was invalid: failed to parse range\n";
++my $from_field_0 = "$prog: range '0' was invalid: fields and positions are numbered from 1\n";
++my $from_field_0_dash = "$prog: range '0-' was invalid: fields and positions are numbered from 1\n";
++my $from_field_0_2 = "$prog: range '0-2' was invalid: fields and positions are numbered from 1\n";
++my $from_pos1 =   "$prog: range '' was invalid: failed to parse range\n";
++my $inval_fld = "$prog: range '--' was invalid: failed to parse range\n";
++my $inval_pos = "$prog: range '--' was invalid: failed to parse range\n";
++my $no_endpoint = "$prog: range '-' was invalid: invalid range with no endpoint\n";
++my $nofield = "$prog: invalid input: The '--delimiter' ('-d') option only usable if printing a sequence of fields\n";
+ 
+ my @Tests =
+  (
+@@ -44,16 +46,16 @@ my @Tests =
+ 
+   # This failed (as it should) even before coreutils-6.9.90,
+   # but cut from 6.9.90 produces a more useful diagnostic.
+-  ['zero-1', '-b0',   {ERR=>$from_pos1}, {EXIT => 1} ],
++  ['zero-1', '-b0',   {ERR=>$from_field_0}, {EXIT => 1} ],
+ 
+   # Up to coreutils-6.9, specifying a range of 0-2 was not an error.
+   # It was treated just like "-2".
+-  ['zero-2', '-f0-2', {ERR=>$from_field1}, {EXIT => 1} ],
++  ['zero-2', '-f0-2', {ERR=>$from_field_0_2}, {EXIT => 1} ],
+ 
+   # Up to coreutils-8.20, specifying a range of 0- was not an error.
+-  ['zero-3b', '-b0-', {ERR=>$from_pos1}, {EXIT => 1} ],
+-  ['zero-3c', '-c0-', {ERR=>$from_pos1}, {EXIT => 1} ],
+-  ['zero-3f', '-f0-', {ERR=>$from_field1}, {EXIT => 1} ],
++  ['zero-3b', '-b0-', {ERR=>$from_field_0_dash}, {EXIT => 1} ],
++  ['zero-3c', '-c0-', {ERR=>$from_field_0_dash}, {EXIT => 1} ],
++  ['zero-3f', '-f0-', {ERR=>$from_field_0_dash}, {EXIT => 1} ],
+ 
+   ['1', '-d:', '-f1,3-', {IN=>"a:b:c\n"}, {OUT=>"a:c\n"}],
+   ['2', '-d:', '-f1,3-', {IN=>"a:b:c\n"}, {OUT=>"a:c\n"}],
+@@ -96,11 +98,10 @@ my @Tests =
+   # Errors
+   # -s may be used only with -f
+   ['y', qw(-s -b4), {IN=>":\n"}, {OUT=>""}, {EXIT=>1},
+-   {ERR=>"$prog: suppressing non-delimited lines makes sense\n"
+-    . "\tonly when operating on fields\n$try"}],
++   {ERR=>"$prog: invalid input: The '--only-delimited' ('-s') option only usable if printing a sequence of fields\n"}],
+   # You must specify bytes or fields (or chars)
+   ['z', '', {IN=>":\n"}, {OUT=>""}, {EXIT=>1},
+-   {ERR=>"$prog: you must specify a list of bytes, characters, or fields\n$try"}
++   {ERR=>"$prog: invalid usage: expects one of --fields (-f), --chars (-c) or --bytes (-b)\n"}
+   ],
+   # Empty field list
+   ['empty-fl', qw(-f ''), {IN=>":\n"}, {OUT=>""}, {EXIT=>1},
+@@ -199,7 +200,7 @@ my @Tests =
+ 
+   # None of the following invalid ranges provoked an error up to coreutils-6.9.
+   ['inval1', qw(-f 2-0), {IN=>''}, {OUT=>''}, {EXIT=>1},
+-   {ERR=>"$prog: invalid decreasing range\n$try"}],
++   {ERR=>"$prog: range '2-0' was invalid: fields and positions are numbered from 1\n"}],
+   ['inval2', qw(-f -), {IN=>''}, {OUT=>''}, {EXIT=>1}, {ERR=>$no_endpoint}],
+   ['inval3', '-f', '4,-', {IN=>''}, {OUT=>''}, {EXIT=>1}, {ERR=>$no_endpoint}],
+   ['inval4', '-f', '1-2,-', {IN=>''}, {OUT=>''}, {EXIT=>1},