makary/phpbb
1
0
Fork 0
mirror of https://github.com/phpbb/phpbb.git synced 2025-06-29 14:48:53 +00:00
Code Issues Projects Releases Packages Wiki Activity

Speed up insertion of new words in mssql and mysql ... lets see what this breaks since the new post/posting isn't commited yet :)

Browse source 
git-svn-id: file:///svn/phpbb/trunk@2076 89ea8834-ac86-4346-8a33-228a782c2dd0
This commit is contained in:
Paul S. Owen 2002-02-11 00:28:17 +00:00
parent 5509abb2ae
commit 056cc59ae0
1 changed files with 121 additions and 141 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

208
phpBB/includes/search.php
View file

@ -19,14 +19,33 @@
* *
***************************************************************************/ ***************************************************************************/
//
// This charset data is borrowed from mnoGoSearch 1.x (http://www.mnogosearch.com/ )
//
$charset_all = "abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789";
$charset = array();
$charset['usacii'] = array();
$charset['iso88591'] = array(0xC0, 0xC1, 0xC2, 0xC3, 0xC4, 0xC5, 0xC6, 0xC7, 0xC8, 0xC9, 0xCA, 0xCB, 0xCC, 0xCD, 0xCE, 0xCF, 0xD0, 0xD1, 0xD2, 0xD3, 0xD4, 0xD5, 0xD6, 0xD8, 0xD9, 0xDA, 0xDB, 0xDC, 0xDD, 0xDE, 0xDF, 0xE0, 0xE1, 0xE2, 0xE3, 0xE4, 0xE5, 0xE6, 0xE7, 0xE8, 0xE9, 0xEA, 0xEB, 0xEC, 0xED, 0xEE, 0xEF, 0xF0, 0xF1, 0xF2, 0xF3, 0xF4, 0xF5, 0xF6, 0xF8, 0xF9, 0xFA, 0xFB, 0xFC, 0xFD, 0xFE, 0xDF, 0); /* Western European */
$charset['iso88592'] = array(193, 195, 194, 196, 161, 198, 200, 199, 207, 201, 204, 203, 202, 208, 205, 206, 197, 165, 163, 209, 210, 211, 212, 214, 213, 192, 216, 166, 169, 170, 171, 222, 218, 220, 219, 217, 221, 175, 172, 174, 223, 225, 227, 226, 228, 177, 230, 232, 231, 239, 233, 236, 235, 234, 240, 237, 238, 229, 181, 179, 241, 242, 243, 244, 246, 245, 224, 248, 182, 185, 186, 187, 254, 250, 252, 251, 249, 253, 191, 188, 190, 223, 0); /* Central European */
$charset['iso88594'] = array(); /* Baltic */
$charset['iso88595'] = array(0xB0, 0xB1, 0xB2, 0xB3, 0xB4, 0xB5, 0xA1, 0xB6, 0xB7, 0xB8, 0xB9, 0xBA, 0xBB, 0xBC, 0xBD, 0xBE, 0xBF, 0xC0, 0xC1, 0xC2, 0xC3, 0xC4, 0xC5, 0xC6, 0xC7, 0xC8, 0xC9, 0xCA, 0xCB, 0xCC, 0xCD, 0xCE, 0xCF, 0xD0, 0xD1, 0xD2, 0xD3, 0xD4, 0xD5, 0xF1, 0xD6, 0xD7, 0xD8, 0xD9, 0xDA, 0xDB, 0xDC, 0xDD, 0xDE, 0xDF, 0xE0, 0xE1, 0xE2, 0xE3, 0xE4, 0xE5, 0xE6, 0xE7, 0xE8, 0xE9, 0xEA, 0xEB, 0xEC, 0xED, 0xEE, 0xEF, 0); /* Cyrillic */
$charset['iso88596'] = array(); /* Arabic */
$charset['iso88597'] = array(0xc1, 0xb6, 0xdc, 0xc2, 0xc3, 0xc4, 0xc5, 0xb8, 0xdd, 0xc6, 0xc7, 0xb9, 0xde, 0xc8, 0xc9, 0xba, 0xda, 0xdf, 0xc0, 0xca, 0xcb, 0xcc, 0xcd, 0xce, 0xcf, 0xbc, 0xfc, 0xd0, 0xd1, 0xd3, 0xf2, 0xd4, 0xd5, 0xbe, 0xdb, 0xfd, 0xfb, 0xe0, 0xd6, 0xd7, 0xd8, 0xd9, 0xbf, 0xfe, 0xe1, 0xe1, 0xe1, 0xe2, 0xe3, 0xe4, 0xe5, 0xe5, 0xe5, 0xe6, 0xe7, 0xe7, 0xe7, 0xe8, 0xe9, 0xe9, 0xe9, 0xe9, 0xe9, 0xea, 0xeb, 0xec, 0xed, 0xee, 0xef, 0xef, 0xef, 0xf0, 0xf1, 0xf3, 0xf3, 0xf4, 0xf5, 0xf5, 0xf5, 0xf5, 0xf5, 0xf5, 0xf6, 0xf7, 0xf8, 0xf9, 0xf9, 0xf9, 0); /* Greek */
$charset['iso88598'] = array(0xE0, 0xE1, 0xE2, 0xE3, 0xE4, 0xE5, 0xE6, 0xE7, 0xE8, 0xE9, 0xEA, 0xEB, 0xEC, 0xED, 0xEE, 0xEF, 0xF0, 0xF1, 0xF2, 0xF3, 0xF4, 0xF5, 0xF6, 0xF7, 0xF8, 0xF9, 0xFA, 0x00); /* Hebrew */
$charset['iso88599'] = array(); /* Turkish */
$charset['iso885913'] = array(); /* Baltic 2 */
$charset['cp1256'] = array(0x8d, 0x8e, 0x90, 0xc1, 0xc2, 0xc3, 0xc4, 0xc5, 0xc6, 0xc7, 0xc8, 0xc9, 0xca, 0xcb, 0xcc, 0xcd, 0xce, 0xcf, 0xd0, 0xd1, 0xd2, 0xd3, 0xd4, 0xd5, 0xd6, 0xd8, 0xd9, 0xda, 0xdb, 0xdc, 0xde, 0xdf, 0xe1, 0xe3, 0xe4, 0xe5, 0xe6, 0xec, 0xed, 0);
$charset[''] = array();
function clean_words($mode, &$entry, &$synonym_list) function clean_words($mode, &$entry, &$synonym_list)
{ {
// Weird, $init_match doesn't work with static when double quotes (") are used... // Weird, $init_match doesn't work with static when double quotes (") are used...
static $drop_char_match = array('^', '$', '&', '(', ')', '<', '>', '`', "'", '|', ',', '@', '_', '?', '%', '-', '~', '+', '.', '[', ']', '{', '}', ':', '\\', '/', '=', '#', '\'', ';', '!'); static $drop_char_match = array('^', '$', '&', '(', ')', '<', '>', '`', "'", '|', ',', '@', '_', '?', '%', '-', '~', '+', '.', '[', ']', '{', '}', ':', '\\', '/', '=', '#', '\'', ';', '!');
static $drop_char_replace = array(" ", " ", " ", " ", " ", " ", " ", " ", "", " ", " ", " ", " ", " ", " ", " ", " ", " ", " ", " ", " ", " ", " ", " ", " " , " ", " ", " ", " ", " ", " "); static $drop_char_replace = array(" ", " ", " ", " ", " ", " ", " ", " ", "", " ", " ", " ", " ", " ", " ", " ", " ", " ", " ", " ", " ", " ", " ", " ", " " , " ", " ", " ", " ", " ", " ");
static $accent_match = array("ß", "à", "á", "â", "ã", "ä", "å", "æ", "ç", "è", "é", "ê", "ë", "ì", "í", "î", "ï", "ð", "ñ", "ò", "ó", "ô", "õ", "ö", "ø", "ù", "ú", "û", "ü", "ý", "þ", "ÿ"); // static $accent_match = array("ß", "à", "á", "â", "ã", "ä", "å", "æ", "ç", "è", "é", "ê", "ë", "ì", "í", "î", "ï", "ð", "ñ", "ò", "ó", "ô", "õ", "ö", "ø", "ù", "ú", "û", "ü", "ý", "þ", "ÿ");
static $accent_replace = array("s", "a", "a", "a", "a", "a", "a", "a", "c", "e", "e", "e", "e", "i", "i", "i", "i", "o", "n", "o", "o", "o", "o", "o", "o", "u", "u", "u", "u", "y", "t", "y"); // static $accent_replace = array("s", "a", "a", "a", "a", "a", "a", "a", "c", "e", "e", "e", "e", "i", "i", "i", "i", "o", "n", "o", "o", "o", "o", "o", "o", "u", "u", "u", "u", "y", "t", "y");
$entry = " " . strip_tags(strtolower($entry)) . " "; $entry = " " . strip_tags(strtolower($entry)) . " ";
@ -117,6 +136,7 @@ function add_search_words($post_id, $post_text, $post_title = "")
while( list($word_in, $search_matches) = @each($search_raw_words) ) while( list($word_in, $search_matches) = @each($search_raw_words) )
{ {
$title_match = ( $word_in == 'title' ) ? 1 : 0; $title_match = ( $word_in == 'title' ) ? 1 : 0;
$value_sql = "";
if( !empty($search_matches) ) if( !empty($search_matches) )
{ {
@ -133,13 +153,7 @@ function add_search_words($post_id, $post_text, $post_title = "")
if( $search_matches[$i] != "" && $search_matches[$i] != $prev_word ) if( $search_matches[$i] != "" && $search_matches[$i] != $prev_word )
{ {
$word[] = $search_matches[$i]; $word[] = $search_matches[$i];
$word_text_sql .= ( ( $word_text_sql != "" ) ? ", " : "" ) . "'" . $search_matches[$i] . "'";
if( $word_text_sql != "" )
{
$word_text_sql .= ", ";
}
$word_text_sql .= "'" . $search_matches[$i] . "'";
} }
$prev_word = $search_matches[$i]; $prev_word = $search_matches[$i];
@ -148,22 +162,18 @@ function add_search_words($post_id, $post_text, $post_title = "")
$sql = "SELECT word_id, word_text, word_common $sql = "SELECT word_id, word_text, word_common
FROM " . SEARCH_WORD_TABLE . " FROM " . SEARCH_WORD_TABLE . "
WHERE word_text IN ($word_text_sql)"; WHERE word_text IN ($word_text_sql)";
$result = $db->sql_query($sql); if( !($result = $db->sql_query($sql)) )
if( !$result )
{ {
message_die(GENERAL_ERROR, "Couldn't select words", "", __LINE__, __FILE__, $sql); message_die(GENERAL_ERROR, "Couldn't select words", "", __LINE__, __FILE__, $sql);
} }
$check_words = array(); $check_words = array();
$word_id_list = array(); $word_id_list = array();
if( $word_check_count = $db->sql_numrows($result) )
{
while( $row = $db->sql_fetchrow($result) ) while( $row = $db->sql_fetchrow($result) )
{ {
$check_words[$row['word_text']] = $row['word_common']; $check_words[$row['word_text']] = $row['word_common'];
$word_id_list[] = $row['word_id']; $word_id_list[] = $row['word_id'];
} }
}
$match_word = array(); $match_word = array();
for ($i = 0; $i < count($word); $i++) for ($i = 0; $i < count($word); $i++)
@ -171,28 +181,58 @@ function add_search_words($post_id, $post_text, $post_title = "")
$new_match = true; $new_match = true;
$word_common = false; $word_common = false;
if( $word_check_count )
{
if( isset($check_words[$word[$i]]) ) if( isset($check_words[$word[$i]]) )
{ {
$new_match = false; $new_match = false;
} }
} else if( empty($check_words[$word[$i]]) )
if( empty($check_words[$word[$i]]) )
{ {
$match_word[] = "'" . $word[$i] . "'"; $match_word[] = "'" . $word[$i] . "'";
} }
if( $new_match ) if( $new_match )
{ {
switch( SQL_LAYER )
{
case 'mysql':
case 'mysql4':
$value_sql .= ( ( $value_sql != "" ) ? ", " : "" ) . "('" . $word[$i] . "', 0)";
break;
case 'mssql':
case 'mssql-odbc':
$value_sql .= ( ( $value_sql != "" ) ? " UNION ALL " : "" ) . "SELECT '" . $word[$i] . "', 0";
break;
default:
$sql = "INSERT INTO " . SEARCH_WORD_TABLE . " (word_text, word_common) $sql = "INSERT INTO " . SEARCH_WORD_TABLE . " (word_text, word_common)
VALUES ('" . $word[$i] . "', 0)"; VALUES ('" . $word[$i] . "', 0)";
$result = $db->sql_query($sql); if( !($result = $db->sql_query($sql)) )
if( !$result )
{ {
message_die(GENERAL_ERROR, "Couldn't insert new word", "", __LINE__, __FILE__, $sql); message_die(GENERAL_ERROR, "Couldn't insert new word", "", __LINE__, __FILE__, $sql);
} }
break;
}
}
}
if ( $value_sql != "" )
{
switch ( SQL_LAYER )
{
case 'mysql':
case 'mysql4':
$sql = "INSERT INTO " . SEARCH_WORD_TABLE . " (word_text, word_common)
VALUES $value_sql";
break;
case 'mssql':
case 'mssql-odbc':
$sql = "INSERT INTO " . SEARCH_WORD_TABLE . " (word_text, word_common)
$value_sql";
break;
}
if( !($result = $db->sql_query($sql)) )
{
message_die(GENERAL_ERROR, "Couldn't insert new word", "", __LINE__, __FILE__, $sql);
} }
} }
@ -200,8 +240,7 @@ function add_search_words($post_id, $post_text, $post_title = "")
SELECT $post_id, word_id, $title_match SELECT $post_id, word_id, $title_match
FROM " . SEARCH_WORD_TABLE . " FROM " . SEARCH_WORD_TABLE . "
WHERE word_text IN ($word_text_sql)"; WHERE word_text IN ($word_text_sql)";
$result = $db->sql_query($sql); if( !($result = $db->sql_query($sql)) )
if( !$result )
{ {
message_die(GENERAL_ERROR, "Couldn't insert new word matches", "", __LINE__, __FILE__, $sql); message_die(GENERAL_ERROR, "Couldn't insert new word matches", "", __LINE__, __FILE__, $sql);
} }
@ -216,23 +255,21 @@ function add_search_words($post_id, $post_text, $post_title = "")
// //
// Check if specified words are too common now // Check if specified words are too common now
// //
function remove_common($mode, $percent, $word_id_list = array()) function remove_common($mode, $fraction, $word_id_list = array())
{ {
global $db; global $db;
$sql = ( $mode == "global" ) ? "SELECT COUNT(DISTINCT post_id) AS total_posts FROM " . SEARCH_MATCH_TABLE : "SELECT SUM(forum_posts) AS total_posts FROM " . FORUMS_TABLE; $sql = ( $mode == "global" ) ? "SELECT COUNT(DISTINCT post_id) AS total_posts FROM " . SEARCH_MATCH_TABLE : "SELECT SUM(forum_posts) AS total_posts FROM " . FORUMS_TABLE;
if( !($result = $db->sql_query($sql)) )
$result = $db->sql_query($sql);
if( !$result )
{ {
message_die(GENERAL_ERROR, "Couldn't obtain post count", "", __LINE__, __FILE__, $sql); message_die(GENERAL_ERROR, "Couldn't obtain post count", "", __LINE__, __FILE__, $sql);
} }
$row = $db->sql_fetchrow($result); $row = $db->sql_fetchrow($result);
if( $row['total_posts'] > 100 ) if( $row['total_posts'] >= 100 )
{ {
$common_threshold = floor($row['total_posts'] * $percent); $common_threshold = floor($row['total_posts'] * $fraction);
$word_id_sql = ""; $word_id_sql = "";
if( $mode == "single" && count($word_id_list) ) if( $mode == "single" && count($word_id_list) )
@ -245,45 +282,37 @@ function remove_common($mode, $percent, $word_id_list = array())
$word_id_sql $word_id_sql
GROUP BY word_id GROUP BY word_id
HAVING COUNT(word_id) > $common_threshold"; HAVING COUNT(word_id) > $common_threshold";
$result = $db->sql_query($sql); if( !($result = $db->sql_query($sql)) )
if( !$result )
{ {
message_die(GENERAL_ERROR, "Couldn't obtain common word list", "", __LINE__, __FILE__, $sql); message_die(GENERAL_ERROR, "Couldn't obtain common word list", "", __LINE__, __FILE__, $sql);
} }
if( $word_count = $db->sql_numrows($result) ) $common_word_id = "";
{
$common_word_id_list = array();
while( $row = $db->sql_fetchrow($result) ) while( $row = $db->sql_fetchrow($result) )
{ {
$common_word_id_list[] = $row['word_id']; $common_word_id = ( $common_word_id != "" ) ? ", " . $row['word_id'] : $row['word_id'];
} }
$db->sql_freeresult($result); $db->sql_freeresult($result);
if( count($common_word_ids) != 0 ) if( $common_word_id != "" )
{ {
$common_word_id_list = implode(", ", $common_word_id_list);
$sql = "UPDATE " . SEARCH_WORD_TABLE . " $sql = "UPDATE " . SEARCH_WORD_TABLE . "
SET word_common = " . TRUE . " SET word_common = " . TRUE . "
WHERE word_id IN ($common_word_id_list)"; WHERE word_id IN ($common_word_id)";
$result = $db->sql_query($sql); if( !($result = $db->sql_query($sql)) )
if( !$result )
{ {
message_die(GENERAL_ERROR, "Couldn't delete word list entry", "", __LINE__, __FILE__, $sql); message_die(GENERAL_ERROR, "Couldn't delete word list entry", "", __LINE__, __FILE__, $sql);
} }
$sql = "DELETE FROM " . SEARCH_MATCH_TABLE . " $sql = "DELETE FROM " . SEARCH_MATCH_TABLE . "
WHERE word_id IN ($common_word_id_list)"; WHERE word_id IN ($common_word_id)";
$result = $db->sql_query($sql); if( !($result = $db->sql_query($sql)) )
if( !$result )
{ {
message_die(GENERAL_ERROR, "Couldn't delete word match entry", "", __LINE__, __FILE__, $sql); message_die(GENERAL_ERROR, "Couldn't delete word match entry", "", __LINE__, __FILE__, $sql);
} }
} }
} }
}
return $word_count; return $word_count;
} }
@ -294,57 +323,6 @@ function remove_unmatched_words()
switch(SQL_LAYER) switch(SQL_LAYER)
{ {
case 'postgresql':
$sql = "DELETE FROM " . SEARCH_WORD_TABLE . "
WHERE word_id NOT IN (
SELECT word_id
FROM " . SEARCH_MATCH_TABLE . "
GROUP BY word_id)";
$result = $db->sql_query($sql);
if( !$result )
{
message_die(GENERAL_ERROR, "Couldn't delete old words from word table", __LINE__, __FILE__, $sql);
}
$unmatched_count = $db->sql_affectedrows();
break;
case 'oracle':
$sql = "DELETE FROM " . SEARCH_WORD_TABLE . "
WHERE word_id IN (
SELECT w.word_id
FROM " . SEARCH_WORD_TABLE . " w, " . SEARCH_MATCH_TABLE . " m
WHERE w.word_id = m.word_id(+)
AND m.word_id IS NULL)";
$result = $db->sql_query($sql);
if( !$result )
{
message_die(GENERAL_ERROR, "Couldn't delete old words from word table", __LINE__, __FILE__, $sql);
}
$unmatched_count = $db->sql_affectedrows();
break;
case 'mssql':
case 'msaccess':
$sql = "DELETE FROM " . SEARCH_WORD_TABLE . "
WHERE word_id IN (
SELECT w.word_id
FROM " . SEARCH_WORD_TABLE . " w
LEFT JOIN " . SEARCH_MATCH_TABLE . " m ON m.word_id = w.word_id
WHERE m.word_id IS NULL)";
$result = $db->sql_query($sql);
if( !$result )
{
message_die(GENERAL_ERROR, "Couldn't delete old words from word table", __LINE__, __FILE__, $sql);
}
$unmatched_count = $db->sql_affectedrows();
break;
case 'mysql': case 'mysql':
case 'mysql4': case 'mysql4':
$sql = "SELECT w.word_id $sql = "SELECT w.word_id
@ -353,41 +331,43 @@ function remove_unmatched_words()
WHERE m.word_id IS NULL"; WHERE m.word_id IS NULL";
if( $result = $db->sql_query($sql) ) if( $result = $db->sql_query($sql) )
{ {
if( $unmatched_count = $db->sql_numrows($result) ) $word_id_sql = "";
{
$rowset = array();
while( $row = $db->sql_fetchrow($result) ) while( $row = $db->sql_fetchrow($result) )
{ {
$rowset[] = $row['word_id']; $word_id_sql .= ( $word_id_sql != "" ) ? ", " . $row['word_id'] : $row['word_id'];
} }
$word_id_sql = implode(", ", $rowset); if( $word_id_sql != "" )
if( $word_id_sql )
{ {
$sql = "DELETE FROM " . SEARCH_WORD_TABLE . " $sql = "DELETE FROM " . SEARCH_WORD_TABLE . "
WHERE word_id IN ($word_id_sql)"; WHERE word_id IN ($word_id_sql)";
$result = $db->sql_query($sql); if( !($result = $db->sql_query($sql, END_TRANSACTION)) )
if( !$result )
{ {
message_die(GENERAL_ERROR, "Couldn't delete word list entry", "", __LINE__, __FILE__, $sql); message_die(GENERAL_ERROR, "Couldn't delete word list entry", "", __LINE__, __FILE__, $sql);
} }
return $db->sql_affectedrows();
} }
else }
break;
default:
$sql = "DELETE FROM " . SEARCH_WORD_TABLE . "
WHERE word_id NOT IN (
SELECT word_id
FROM " . SEARCH_MATCH_TABLE . "
GROUP BY word_id)";
if( !($result = $db->sql_query($sql, END_TRANSACTION)) )
{ {
return 0; message_die(GENERAL_ERROR, "Couldn't delete old words from word table", __LINE__, __FILE__, $sql);
}
}
else
{
return 0;
}
} }
return $db->sql_affectedrows();
break; break;
} }
return $unmatched_count; return 0;
} }
?> ?>