Why does adding a common suffix cancel the sort order in the en_US locale?

Question

Following code

#!/usr/bin/perl

use strict;
use warnings;

my $s1 = '[e-mail]';
my $s2 = '[e-mail]';
my $s3 = 'aaa2000';
my $s4 = 'aaa_2000';

no locale;

print "\nNO Locale:\n\n";

if ($s1 gt $s2) {print "$s1 is > $s2\n";}
if ($s1 lt $s2) {print "$s1 is < $s2\n";}
if ($s1 eq $s2) {print "$s1 is = $s2\n";}

if ($s3 gt $s4) {print "$s3 is > $s4\n";}
if ($s3 lt $s4) {print "$s3 is < $s4\n";}
if ($s3 eq $s4) {print "$s3 is = $s4\n";}

use locale;

print "\nWith 'use locale;':\n\n";

if ($s1 gt $s2) {print "$s1 is > $s2\n";}
if ($s1 lt $s2) {print "$s1 is < $s2\n";}
if ($s1 eq $s2) {print "$s1 is = $s2\n";}

if ($s3 gt $s4) {print "$s3 is > $s4\n";}
if ($s3 lt $s4) {print "$s3 is < $s4\n";}
if ($s3 eq $s4) {print "$s3 is = $s4\n";}

displays

NO Locale:

[e-mail] is < [e-mail]
aaa2000 is < aaa_2000

With 'use locale;':

[e-mail] is > [e-mail]
aaa2000 is < aaa_2000

which I cannot follow: at the same time, when using the locale, there is <b And [e-mail] > [e-mail] ? !!

Am I missing something more or less obvious, or is this a mistake? Can others confirm that they see the same behavior?

Locale is $ locale
LANG=en_US.UTF-8
LC_CTYPE="en_US.UTF-8"
LC_NUMERIC="en_US.UTF-8"
LC_TIME="en_US.UTF-8"
LC_COLLATE="en_US.UTF-8"
LC_MONETARY="en_US.UTF-8"
LC_MESSAGES="en_US.UTF-8"
LC_PAPER="en_US.UTF-8"
LC_NAME="en_US.UTF-8"
LC_ADDRESS="en_US.UTF-8"
LC_TELEPHONE="en_US.UTF-8"
LC_MEASUREMENT="en_US.UTF-8"
LC_IDENTIFICATION="en_US.UTF-8"
LC_ALL=

Thanks in advance.

Answer 1

. , . @ _, , , , . ,

[e-mail] > [e-mail]

,

aaa2000yahoocom = aaa2000yahoocom

( )

@. > _@.

@ _. ( , , - ISO .)

. C- strxfrm(A) cmp strxfrm(B). :

use POSIX;

my $s1 = '[e-mail]';
my $s2 = '[e-mail]';

foreach ($s1, $s2) {
    printf "%s =>\t%v02x\n", $_, POSIX::strxfrm($_);
}

:

[e-mail] =>    0c.0c.0c.04.02.02.02.24.0c.13.1a.1a.0e.1a.18.01.08.08.08.08.08.08.08.08.08.08.08.08.08.08.08.01.02.02.02.02.02.02.02.02.02.02.02.02.02.02.02.01.08.5d.06.44
# explanation:           a  a  a  2  0  0  0  y  a  h  o  o  c  o  m DIV secondary weights ...                       DIV tertiary weights ...                        DIV  @     .
[e-mail] =>   0c.0c.0c.04.02.02.02.24.0c.13.1a.1a.0e.1a.18.01.08.08.08.08.08.08.08.08.08.08.08.08.08.08.08.01.02.02.02.02.02.02.02.02.02.02.02.02.02.02.02.01.04.36.05.5d.06.44
# explanation:           a  a  a  2  0  0  0  y  a  h  o  o  c  o  m DIV secondary weights ...                       DIV tertiary weights ...                        DIV  _     @     .

- ; , . , .

Answer 2

32- Linux en_US.utf8. Perl, C:

#include <locale.h>
#include <string.h>
#include <stdio.h>

void transformed(const char* str)
{
  char dest[256];
  const char* c;

  strxfrm(dest, str, sizeof(dest));
  printf("%18s =", str);
  for (c = dest; *c; ++c) printf(" %02x", *c);
  puts("");
} /* end transformed */

void test_strings(const char* s1, const char* s2)
{
  int c = strcoll(s1, s2);

  printf("%s is %s %s\n", s1, ((c < 0) ? "<" : ((c == 0) ? "=" : ">")), s2);
} /* end test_strings */

int main(int argc, char* argv[])
{
  puts("with C locale:");

  test_strings("[e-mail]", "[e-mail]");
  test_strings("aaa2000", "aaa_2000");

  setlocale(LC_ALL, "");
  puts("\nwith your locale:");

  test_strings("[e-mail]", "[e-mail]");
  test_strings("aaa2000", "aaa_2000");
  puts("");
  transformed("[e-mail]");
  transformed("[e-mail]");
  transformed("aaa2000");
  transformed("aaa_2000");
  return 0;
} /* end main */

LANG=en_US.utf8 :

with C locale:
[e-mail] is < [e-mail]
aaa2000 is < aaa_2000

with your locale:
[e-mail] is > [e-mail]
aaa2000 is < aaa_2000

 [e-mail] = 0c 0c 0c 04 02 02 02 24 0c 13 1a 1a 0e 1a 18 01 08 08 08 08 08 08 08 08 08 08 08 08 08 08 08 01 02 02 02 02 02 02 02 02 02 02 02 02 02 02 02 01 08 5d 06 44
[e-mail] = 0c 0c 0c 04 02 02 02 24 0c 13 1a 1a 0e 1a 18 01 08 08 08 08 08 08 08 08 08 08 08 08 08 08 08 01 02 02 02 02 02 02 02 02 02 02 02 02 02 02 02 01 04 36 05 5d 06 44
           aaa2000 = 0c 0c 0c 04 02 02 02 01 08 08 08 08 08 08 08 01 02 02 02 02 02 02 02
          aaa_2000 = 0c 0c 0c 04 02 02 02 01 08 08 08 08 08 08 08 01 02 02 02 02 02 02 02 01 04 36

strxfrm ( Perl POSIX) , . byte-for-byte, , , .

, . , , en_US. , C .