From 497d1bfe0283598021f2be2bd6664ac8bbab25ce Mon Sep 17 00:00:00 2001
From: Evan Prodromou <evan@controlyourself.ca>
Date: Wed, 27 May 2009 19:12:37 -0400
Subject: Add fixup_utf8 to fixup problems with UTF-8 in a database

Fixes up an old database to store strings in UTF-8. Hopefully works!
---
 scripts/fixup_utf8.php | 131 +++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 131 insertions(+)
 create mode 100644 scripts/fixup_utf8.php

diff --git a/scripts/fixup_utf8.php b/scripts/fixup_utf8.php
new file mode 100644
index 000000000..0763c72c9
--- /dev/null
+++ b/scripts/fixup_utf8.php
@@ -0,0 +1,131 @@
+#!/usr/bin/env php
+<?php
+/*
+ * Laconica - a distributed open-source microblogging tool
+ * Copyright (C) 2009, Control Yourself, Inc.
+ *
+ * This program is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU Affero General Public License for more details.
+ *
+ * You should have received a copy of the GNU Affero General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+# Abort if called from a web server
+if (isset($_SERVER) && array_key_exists('REQUEST_METHOD', $_SERVER)) {
+    print "This script must be run from the command line\n";
+    exit(1);
+}
+
+ini_set("max_execution_time", "0");
+ini_set("max_input_time", "0");
+set_time_limit(0);
+mb_internal_encoding('UTF-8');
+
+define('INSTALLDIR', realpath(dirname(__FILE__) . '/..'));
+define('LACONICA', true);
+
+require_once(INSTALLDIR . '/lib/common.php');
+require_once('DB.php');
+
+function main() {
+
+    $dbl = doConnect('latin1');
+
+    if (empty($dbl)) {
+        return;
+    }
+
+    $dbu = doConnect('utf8');
+
+    if (empty($dbu)) {
+        return;
+    }
+
+    // Do a separate DB connection
+
+    $sth = $dbu->prepare("UPDATE notice SET content = UNHEX(?), rendered = UNHEX(?) WHERE id = ?");
+
+    if (PEAR::isError($sth)) {
+        echo "ERROR: " . $sth->getMessage() . "\n";
+        return;
+    }
+
+    $rn = $dbl->query('SELECT id, content, rendered FROM notice ' .
+                      'WHERE LENGTH(content) != CHAR_LENGTH(content)');
+
+    if (PEAR::isError($rn)) {
+        echo "ERROR: " . $rn->getMessage() . "\n";
+        return;
+    }
+
+    echo "Number of rows: " . $rn->numRows() . "\n";
+
+    $notice = array();
+
+    while (DB_OK == $rn->fetchInto($notice)) {
+
+        $id = ($notice[0])+0;
+        $content = bin2hex($notice[1]);
+        $rendered = bin2hex($notice[2]);
+
+        echo "$id...";
+
+        $result =& $dbu->execute($sth, array($content, $rendered, $id));
+
+        if (PEAR::isError($result)) {
+            echo "ERROR: " . $result->getMessage() . "\n";
+            continue;
+        }
+
+        $cnt = $dbu->affectedRows();
+
+        if ($cnt != 1) {
+            echo "ERROR: 0 rows affected\n";
+            continue;
+        }
+
+        $notice = Notice::staticGet('id', $id);
+        $notice->decache();
+
+        echo "OK\n";
+    }
+}
+
+function doConnect($charset)
+{
+    $db = DB::connect(common_config('db', 'database'),
+                      array('persistent' => false));
+
+    if (PEAR::isError($db)) {
+        echo "ERROR: " . $db->getMessage() . "\n";
+        return NULL;
+    }
+
+    $result = $db->query("SET NAMES $charset");
+
+    if (PEAR::isError($result)) {
+        echo "ERROR: " . $result->getMessage() . "\n";
+        $db->disconnect();
+        return NULL;
+    }
+
+    $result = $db->autoCommit(true);
+
+    if (PEAR::isError($result)) {
+        echo "ERROR: " . $result->getMessage() . "\n";
+        $db->disconnect();
+        return NULL;
+    }
+
+    return $db;
+}
+
+main();
-- 
cgit v1.2.3