Rev bump. Add some patches for MySQL, see ebuild for further details.

(Portage version: 2.1.10.11/cvs/Linux i686)

5 files changed, 251 insertions, 7 deletions

diff --git a/mail-filter/spamassassin/ChangeLog b/mail-filter/spamassassin/ChangeLog
index b649054b9855..3936443664c4 100644
--- a/mail-filter/spamassassin/ChangeLog
+++ b/mail-filter/spamassassin/ChangeLog
@@ -1,6 +1,14 @@
 # ChangeLog for mail-filter/spamassassin
 # Copyright 1999-2011 Gentoo Foundation; Distributed under the GPL v2
-# $Header: /var/cvsroot/gentoo-x86/mail-filter/spamassassin/ChangeLog,v 1.202 2011/09/14 23:00:38 polynomial-c Exp $
+# $Header: /var/cvsroot/gentoo-x86/mail-filter/spamassassin/ChangeLog,v 1.203 2011/11/27 19:44:24 idl0r Exp $
+
+*spamassassin-3.3.2-r1 (27 Nov 2011)
+
+  27 Nov 2011; Christian Ruppert <idl0r@gentoo.org> -spamassassin-3.3.2.ebuild,
+  +spamassassin-3.3.2-r1.ebuild, +files/spamassassin-3.3.2-binary_token.patch,
+  +files/spamassassin-3.3.2-innodb.patch,
+  +files/spamassassin-3.3.2-mysql_count_rows.patch:
+  Rev bump. Add some patches for MySQL, see ebuild for further details.
 
   14 Sep 2011; Lars Wendler <polynomial-c@gentoo.org> files/3.3.1-spamd.init:
   non-maintainer commit: Moved reload option from extra_commands to
diff --git a/mail-filter/spamassassin/files/spamassassin-3.3.2-binary_token.patch b/mail-filter/spamassassin/files/spamassassin-3.3.2-binary_token.patch
new file mode 100644
index 000000000000..5ce5c0d90827
--- /dev/null
+++ b/mail-filter/spamassassin/files/spamassassin-3.3.2-binary_token.patch
@@ -0,0 +1,13 @@
+Index: sql/bayes_mysql.sql
+===================================================================
+--- sql/bayes_mysql.sql	(revision 1139005)
++++ sql/bayes_mysql.sql	(working copy)
+@@ -22,7 +22,7 @@
+ 
+ CREATE TABLE bayes_token (
+   id int(11) NOT NULL default '0',
+-  token char(5) NOT NULL default '',
++  token binary(5) NOT NULL default '',
+   spam_count int(11) NOT NULL default '0',
+   ham_count int(11) NOT NULL default '0',
+   atime int(11) NOT NULL default '0',
diff --git a/mail-filter/spamassassin/files/spamassassin-3.3.2-innodb.patch b/mail-filter/spamassassin/files/spamassassin-3.3.2-innodb.patch
new file mode 100644
index 000000000000..8bf13720c6e1
--- /dev/null
+++ b/mail-filter/spamassassin/files/spamassassin-3.3.2-innodb.patch
@@ -0,0 +1,114 @@
+Index: sql/README.bayes
+===================================================================
+--- sql/README.bayes	(revision 1139008)
++++ sql/README.bayes	(working copy)
+@@ -17,27 +17,37 @@
+ bayes_store_module		   Mail::SpamAssassin::BayesStore::SQL
+ 
+ This directive is used by the Bayes module to determine which storage
+-module should be used.  If not set it will default to:
++module should be used. If not set it will default to:
+ Mail::SpamAssassin::BayesStore::DBM
+ 
++The storage module Mail::SpamAssassin::BayesStore::SQL is an older generic
++SQL module which can be also be used with versions of MySQL which did not
++have support for an InnoDB engine and transactions. If choosing this module
++consider replacing the InnoDB engine with MyISAM (explicitly or defaulted)
++in the schema (files bayes_mysql.sql and awl_mysql.sql). Note that old
++versions of MySQL expect syntax TYPE=MyISAM instead of ENGINE=MyISAM,
++while newer versions throw a syntax error on TYPE and only allow ENGINE.
++In short: replace ENGINE=InnoDB with TYPE=MyISAM (or just leave it out)
++in the bayes_mysql.sql and awl_mysql.sql schemas if ENGINE=InnoDB is not
++accepted.
++
++There is also a MySQL specific storage driver available to provides a
++small boost in performance.  It requires version 4.1 or above of the
++MySQL database software to work properly.  In addition, it provides
++rollback on error functionality if you create your bayes database table
++using the InnoDB storage engine. WARNING: Using this module with a version
++of MySQL < 4.1 could have unexpected results.  To use the MySQL 4.1+
++specific module set your bayes_store_module directive accordingly:
++  bayes_store_module               Mail::SpamAssassin::BayesStore::MySQL
++
+ PostgreSQL users will want to use the PostgreSQL specific storage
+ module:
+-bayes_store_module               Mail::SpamAssassin::BayesStore::PgSQL
++  bayes_store_module               Mail::SpamAssassin::BayesStore::PgSQL
+ This module provides a slightly different interface to makes better
+ use of the resources that PostgreSQL offers.  In addition, please make
+ sure that you follow the instructions below for loading the proper
+ procedural language and installing the tables and stored procedure.
+ 
+-There is also a MySQL specific storage driver available to provides a
+-small boost in performance.  It requires version 4.1 or above of the
+-MySQL database software to work properly.  In addition, it provides
+-rollback on error functionality if you create your bayes database
+-table using the InnoDB storage engine (ie s/MyISAM/InnoDB/ on the
+-bayes_mysql.sql file).  WARNING: Using this module with a version of
+-MySQL < 4.1 could have unexpected results.  To use the MySQL 4.1+
+-specific module set your bayes_store_module directive accordingly:
+-bayes_store_module               Mail::SpamAssassin::BayesStore::MySQL
+-
+ Additional configuration directives provided by BayesSQL:
+ 
+ bayes_sql_dsn			   DBI:driver:database:hostname[:port]
+Index: sql/awl_mysql.sql
+===================================================================
+--- sql/awl_mysql.sql	(revision 1139008)
++++ sql/awl_mysql.sql	(working copy)
+@@ -1,9 +1,9 @@
+ CREATE TABLE awl (
+   username varchar(100) NOT NULL default '',
+-  email varchar(255) NOT NULL default '',
++  email varbinary(255) NOT NULL default '',
+   ip varchar(40) NOT NULL default '',
+   count int(11) NOT NULL default '0',
+   totscore float NOT NULL default '0',
+   signedby varchar(255) NOT NULL default '',
+   PRIMARY KEY (username,email,signedby,ip)
+-) TYPE=MyISAM;
++) ENGINE=InnoDB;
+Index: sql/bayes_mysql.sql
+===================================================================
+--- sql/bayes_mysql.sql	(revision 1139008)
++++ sql/bayes_mysql.sql	(working copy)
+@@ -3,13 +3,13 @@
+   id int(11) NOT NULL default '0',
+   runtime int(11) NOT NULL default '0',
+   KEY bayes_expire_idx1 (id)
+-) TYPE=MyISAM;
++) ENGINE=InnoDB;
+ 
+ CREATE TABLE bayes_global_vars (
+   variable varchar(30) NOT NULL default '',
+   value varchar(200) NOT NULL default '',
+   PRIMARY KEY  (variable)
+-) TYPE=MyISAM;
++) ENGINE=InnoDB;
+ 
+ INSERT INTO bayes_global_vars VALUES ('VERSION','3');
+ 
+@@ -18,7 +18,7 @@
+   msgid varchar(200) binary NOT NULL default '',
+   flag char(1) NOT NULL default '',
+   PRIMARY KEY  (id,msgid)
+-) TYPE=MyISAM;
++) ENGINE=InnoDB;
+ 
+ CREATE TABLE bayes_token (
+   id int(11) NOT NULL default '0',
+@@ -28,7 +28,7 @@
+   atime int(11) NOT NULL default '0',
+   PRIMARY KEY  (id, token),
+   INDEX bayes_token_idx1 (id, atime)
+-) TYPE=MyISAM;
++) ENGINE=InnoDB;
+ 
+ CREATE TABLE bayes_vars (
+   id int(11) NOT NULL AUTO_INCREMENT,
+@@ -43,4 +43,4 @@
+   newest_token_age int(11) NOT NULL default '0',
+   PRIMARY KEY  (id),
+   UNIQUE bayes_vars_idx1 (username)
+-) TYPE=MyISAM;
++) ENGINE=InnoDB;
diff --git a/mail-filter/spamassassin/files/spamassassin-3.3.2-mysql_count_rows.patch b/mail-filter/spamassassin/files/spamassassin-3.3.2-mysql_count_rows.patch
new file mode 100644
index 000000000000..54ee5573dadc
--- /dev/null
+++ b/mail-filter/spamassassin/files/spamassassin-3.3.2-mysql_count_rows.patch
@@ -0,0 +1,88 @@
+--- lib/Mail/SpamAssassin/BayesStore/MySQL.pm	(revision 1138970)
++++ lib/Mail/SpamAssassin/BayesStore/MySQL.pm	(working copy)
+@@ -840,14 +840,28 @@
+       return 0;
+     }
+ 
++    # With ON DUPLICATE KEY UPDATE, the affected-rows value per row is 1 if
++    # the row is inserted as a new row and 2 if an existing row is updated.
++    #
++    # Due to a MySQL server bug a value of 3 can be seen.
++    # See: http://bugs.mysql.com/bug.php?id=46675
++    #   When executing the INSERT ... ON DUPLICATE KEY UPDATE statement
++    #   and checking the rows return count:
++    #   mysql_client_found_rows = 0: The second INSERT returns a row count
++    #                                of 2 in all MySQL versions.
++    #   mysql_client_found_rows = 1: The second INSERT returns this row count:
++    #     Before MySQL 5.1.20: 2
++    #     MySQL 5.1.20: undef on Mac OS X, 139775481 on Linux (garbage?)
++    #     MySQL 5.1.21 and up: 3
++    #
+     my $num_rows = $rc;
+ 
+     $sth->finish();
+ 
+-    if ($num_rows == 1 || $num_rows == 2) {
++    if ($num_rows == 1 || $num_rows == 2 || $num_rows == 3) {
+       my $token_count_update = '';
+       
+-      $token_count_update = "token_count = token_count + 1," if ($num_rows == 1);
++      $token_count_update = "token_count = token_count + 1," if $num_rows == 1;
+       $sql = "UPDATE bayes_vars SET
+                      $token_count_update
+                      newest_token_age = GREATEST(newest_token_age, ?),
+@@ -872,7 +886,11 @@
+     }
+     else {
+       # $num_rows was not what we expected
+-      dbg("bayes: _put_token: Updated an unexpected number of rows.");
++      my $token_displ = $token;
++      $token_displ =~ s/(.)/sprintf('%02x',ord($1))/egs;
++      dbg("bayes: _put_token: Updated an unexpected number of rows: %s, ".
++          "id: %s, token (hex): %s",
++          $num_rows, $self->{_userid}, $token_displ);
+       $self->{_dbh}->rollback();
+       return 0;
+     }
+@@ -987,8 +1005,24 @@
+       else {
+ 	my $num_rows = $rc;
+ 
+-	$need_atime_update_p = 1 if ($num_rows == 1 || $num_rows == 2);
+-	$new_tokens++ if ($num_rows == 1);
++        # With ON DUPLICATE KEY UPDATE, the affected-rows value per row is 1 if
++        # the row is inserted as a new row and 2 if an existing row is updated.
++        # But see MySQL bug (as above): http://bugs.mysql.com/bug.php?id=46675
++
++        if ($num_rows == 1) {
++          $new_tokens++;
++          $need_atime_update_p = 1;
++        } elsif ($num_rows == 2 || $num_rows == 3) {
++          $need_atime_update_p = 1;
++        } else {
++          # $num_rows was not what we expected
++          my $token_displ = $token;
++          $token_displ =~ s/(.)/sprintf('%02x',ord($1))/egs;
++          dbg("bayes: _put_tokens: Updated an unexpected number of rows: %s, ".
++              "id: %s, token (hex): %s",
++              $num_rows, $self->{_userid}, $token_displ);
++          $error_p = 1;
++        }
+       }
+     }
+ 
+@@ -1026,10 +1060,10 @@
+       }
+     }
+     else {
+-      # $num_rows was not what we expected
+-      dbg("bayes: _put_tokens: Updated an unexpected number of rows.");
+-      $self->{_dbh}->rollback();
+-      return 0;
++      info("bayes: _put_tokens: no atime updates needed?  Num of tokens: %d",
++           scalar keys %{$tokens});
++#     $self->{_dbh}->rollback();
++#     return 0;
+     }
+   }
+ 
diff --git a/mail-filter/spamassassin/spamassassin-3.3.2.ebuild b/mail-filter/spamassassin/spamassassin-3.3.2-r1.ebuild
index 193626d25f0c..20eefe2b1483 100644
--- a/mail-filter/spamassassin/spamassassin-3.3.2.ebuild
+++ b/mail-filter/spamassassin/spamassassin-3.3.2-r1.ebuild
@@ -1,6 +1,6 @@
 # Copyright 1999-2011 Gentoo Foundation
 # Distributed under the terms of the GNU General Public License v2
-# $Header: /var/cvsroot/gentoo-x86/mail-filter/spamassassin/spamassassin-3.3.2.ebuild,v 1.1 2011/06/25 13:30:11 tove Exp $
+# $Header: /var/cvsroot/gentoo-x86/mail-filter/spamassassin/spamassassin-3.3.2-r1.ebuild,v 1.1 2011/11/27 19:44:24 idl0r Exp $
 
 EAPI=4
 
@@ -8,7 +8,7 @@ inherit perl-module toolchain-funcs eutils
 
 MY_P=Mail-SpamAssassin-${PV//_/-}
 S=${WORKDIR}/${MY_P}
-DESCRIPTION="SpamAssassin is an extensible email filter which is used to identify spam."
+DESCRIPTION="SpamAssassin is an extensible email filter which is used to identify spam"
 HOMEPAGE="http://spamassassin.apache.org/"
 SRC_URI="mirror://apache/spamassassin/source/${MY_P}.tar.bz2"
 
@@ -61,6 +61,19 @@ RDEPEND="${DEPEND}"
 
 SRC_TEST="do"
 
+src_prepare() {
+	# http://old.nabble.com/Migrating-bayes-to-mysql-fails-with-parsing-errors-td31889789i20.html
+
+	# https://issues.apache.org/SpamAssassin/show_bug.cgi?id=6624
+	epatch "${FILESDIR}/${P}-mysql_count_rows.patch"
+
+	#https://issues.apache.org/SpamAssassin/show_bug.cgi?id=6625
+	epatch "${FILESDIR}/${P}-binary_token.patch"
+
+	# https://issues.apache.org/SpamAssassin/show_bug.cgi?id=6626
+	epatch "${FILESDIR}/${P}-innodb.patch"
+}
+
 src_configure() {
 	# - Set SYSCONFDIR explicitly so we can't get bitten by bug 48205 again
 	#	(just to be sure, nobody knows how it could happen in the first place).
@@ -129,13 +142,21 @@ src_install () {
 	newinitd "${FILESDIR}"/3.3.1-spamd.init spamd
 	newconfd "${FILESDIR}"/3.0.0-spamd.conf spamd
 
-	use postgres && \
-		sed -i -e 's:@USEPOSTGRES@::' "${D}/etc/init.d/spamd" || \
+	if use postgres; then
+		sed -i -e 's:@USEPOSTGRES@::' "${D}/etc/init.d/spamd"
+
+		dodoc sql/*_pg.sql
+	else
 		sed -i -e '/@USEPOSTGRES@/d' "${D}/etc/init.d/spamd"
+	fi
+
+	if use mysql; then
+		sed -i -e 's:@USEMYSQL@::' "${D}/etc/init.d/spamd"
 
-	use mysql && \
-		sed -i -e 's:@USEMYSQL@::' "${D}/etc/init.d/spamd" || \
+		dodoc sql/*_mysql.sql
+	else
 		sed -i -e '/@USEMYSQL@/d' "${D}/etc/init.d/spamd"
+	fi
 
 	dodoc NOTICE TRADEMARK CREDITS INSTALL.VMS UPGRADE USAGE \
 		sql/README.bayes sql/README.awl procmailrc.example sample-nonspam.txt \