PT-2279 - Option --charset is confusing when set to utf8mb4

- Added pattern check for utf8 character set instead of eq
- Added test cases

bin/pt-archiver

@@ -6786,8 +6786,8 @@ sub main {
    }
 
    my $charset  = $got_charset || '';
-   if ($charset eq 'utf8') {
+   if ($charset =~ m/utf8/) {
-      $charset = ":$charset";
+      $charset = ":utf8";
    }
    elsif ($charset) {
       eval { require Encode }

t/pt-archiver/pt-2279.t

@@ -0,0 +1,80 @@
+#!/usr/bin/env perl
+
+BEGIN {
+   die "The PERCONA_TOOLKIT_BRANCH environment variable is not set.\n"
+      unless $ENV{PERCONA_TOOLKIT_BRANCH} && -d $ENV{PERCONA_TOOLKIT_BRANCH};
+   unshift @INC, "$ENV{PERCONA_TOOLKIT_BRANCH}/lib";
+};
+
+use strict;
+use warnings FATAL => 'all';
+use English qw(-no_match_vars);
+use Test::More;
+
+use charnames ':full';
+
+use PerconaTest;
+use Sandbox;
+require "$trunk/bin/pt-archiver";
+
+my $dp  = new DSNParser(opts=>$dsn_opts);
+my $sb  = new Sandbox(basedir => '/tmp', DSNParser => $dp);
+my $dbh = $sb->get_dbh_for('master');
+
+if ( !$dbh ) {
+   plan skip_all => 'Cannot connect to sandbox master';
+}
+
+my $output;
+my $cnf = "/tmp/12345/my.sandbox.cnf";
+my $cmd = "$trunk/bin/pt-archiver";
+
+$sb->wipe_clean($dbh);
+$sb->create_dbs($dbh, ['test']);
+
+# Test --bulk-insert
+$sb->load_file('master', 't/pt-archiver/samples/pt-2279.sql');
+
+$output = output(
+   sub { pt_archiver::main(qw(--limit 50 --bulk-insert),
+      qw(--bulk-delete --where 1=1 --statistics --charset utf8mb4),
+      '--source', "L=1,D=test,t=table_1,F=$cnf",
+      '--dest',   "t=table_1_dest") },
+);
+
+unlike(
+   $output,
+   qr/Cannot find encoding "utf8mb4"/,
+   'Bulk insert does not fail due to missing utf8mb4'
+) or diag($output);
+
+# Test --file
+$sb->load_file('master', 't/pt-archiver/samples/pt-2279.sql');
+
+$output = output(
+   sub { pt_archiver::main(qw(--limit 50),
+      qw(--where 1=1 --statistics --charset utf8mb4),
+      '--source', "L=1,D=test,t=table_1,F=$cnf",
+      '--file',   '/tmp/%Y-%m-%d-%D_%H:%i:%s.%t') },
+);
+
+unlike(
+   $output,
+   qr/Cannot find encoding "utf8mb4"/,
+   'Destination file does not fail due to missing utf8mb4'
+) or diag($output);
+
+unlike(
+   $output,
+   qr/Cannot open :encoding(utf8mb4)/,
+   'Destination file can be read if encodin utf8mb4 is used'
+) or diag($output);
+
+# #############################################################################
+# Done.
+# #############################################################################
+diag(`rm -f /tmp/*.table_1`);
+$sb->wipe_clean($dbh);
+ok($sb->ok(), "Sandbox servers") or BAIL_OUT(__FILE__ . " broke the sandbox");
+done_testing;
+exit;

t/pt-archiver/samples/pt-2279.sql

@@ -0,0 +1,18 @@
+DROP TABLE IF EXISTS test.table_1;
+DROP TABLE IF EXISTS test.table_1_dest;
+
+SET NAMES utf8mb4;
+
+CREATE TABLE test.table_1 (
+    id int(11) NOT NULL,
+    c1 varchar(20) DEFAULT NULL,
+    PRIMARY KEY (id)
+) ENGINE=InnoDB DEFAULT CHARSET=utf8mb4;
+
+INSERT INTO test.table_1 VALUES(1, 'I love MySQL! 🐬');
+
+CREATE TABLE test.table_1_dest (
+    id int(11) NOT NULL,
+    c1 varchar(10) DEFAULT NULL,
+    PRIMARY KEY (id)
+) ENGINE=InnoDB DEFAULT CHARSET=utf8mb4;