| 包 | XS |
|---|---|
| 继承关系 | class XSIndex » XSServer » XSComponent |
| 版本 | 1.0.0 |
| 源代码 | sdk/php/lib/XSIndex.class.php |
| 名称 | 类型 | 描述 | 定义于 |
|---|---|---|---|
| connString | string | 连接字符串 | XSServer |
| customDict | string | 获取自定义词典内容 | XSIndex |
| project | string | 获取当前项目名称 | XSServer |
| respond | XSCommand | 从服务器读取响应指令 | XSServer |
| scwsMulti | int | 获取当前索引库的分词复合等级 | XSIndex |
| socket | mixed | 获取连接资源描述符 | XSServer |
| xs | XS | 服务端关联的 XS 对象 | XSServer |
| 名称 | 类型 | 描述 | 定义于 |
|---|---|---|---|
| _conn | XSServer | ||
| _flag | XSServer | ||
| _project | XSServer | ||
| _sendBuffer | XSServer | ||
| _sock | XSServer |
| 名称 | 描述 | 定义于 |
|---|---|---|
| __construct() | 构造函数, 打开连接 | XSServer |
| __destruct() | 析构函数 | XSIndex |
| __get() | 魔术方法 __get | XSComponent |
| __isset() | 魔术方法 __isset | XSComponent |
| __set() | 魔术方法 __set | XSComponent |
| __unset() | 魔术方法 __unset | XSComponent |
| add() | 添加文档到索引中 | XSIndex |
| addExdata() | 批量提交索引命令封包数据 | XSIndex |
| addServer() | 增加一个同步索引服务器 | XSIndex |
| addSynonym() | 添加同义词 | XSIndex |
| beginRebuild() | 开始重建索引 | XSIndex |
| clean() | 完全清空索引数据 | XSIndex |
| close() | 关闭索引服务端连接 | XSIndex |
| closeBuffer() | 提交所有指令并关闭缓冲区 | XSIndex |
| del() | 删除索引中的数据 | XSIndex |
| delSynonym() | 删除某个同义词 | XSIndex |
| endRebuild() | 完成并关闭重建索引 | XSIndex |
| execCommand() | 执行服务端指令并获取返回值 | XSIndex |
| flushIndex() | 强制刷新服务端的当前库的索引缓存 | XSIndex |
| flushLogging() | 强制刷新服务端当前项目的搜索日志 | XSIndex |
| getConnString() | Returns 连接字符串 | XSServer |
| getCustomDict() | 获取自定义词典内容 | XSIndex |
| getProject() | 获取当前项目名称 | XSServer |
| getRespond() | 从服务器读取响应指令 | XSServer |
| getScwsMulti() | 获取当前索引库的分词复合等级 | XSIndex |
| getSocket() | 获取连接资源描述符 | XSServer |
| hasRespond() | 判断服务端是否有可读数据 | XSServer |
| open() | 打开服务端连接 | XSServer |
| openBuffer() | 开启索引命令提交缓冲区 | XSIndex |
| reopen() | 重新打开连接 | XSServer |
| sendCommand() | 往服务器直接发送指令 (无缓存) | XSServer |
| setCustomDict() | 设置自定义词典内容 | XSIndex |
| setDb() | 更改存放索引数据的目录 | XSIndex |
| setProject() | 设置当前项目 | XSServer |
| setScwsMulti() | 设置当前索引库的分词复合等级 | XSIndex |
| setTimeout() | 设置服务端超时秒数 | XSServer |
| stopRebuild() | 中止索引重建 | XSIndex |
| update() | 更新索引文档 | XSIndex |
| 名称 | 描述 | 定义于 |
|---|---|---|
| check() | 检测服务端的连接情况 | XSServer |
| connect() | 连接服务端 | XSServer |
| read() | 读取数据 | XSServer |
| write() | 写入数据 | XSServer |
获取自定义词典内容
获取当前索引库的分词复合等级
|
public void __destruct()
|
public function __destruct()
{
if ($this->_rebuild === true) {
try {
$this->endRebuild();
} catch (Exception $e) {
}
}
foreach (self::$_adds as $srv) {
$srv->close();
}
self::$_adds = array();
parent::__destruct();
}
析构函数 在此自动关闭开启的 rebuild
|
public XSIndex add(XSDocument $doc)
| ||
| $doc | XSDocument | |
| {return} | XSIndex | 返回自身对象以支持串接操作 |
public function add(XSDocument $doc)
{
return $this->update($doc, true);
}
添加文档到索引中 特别要注意的是: 系统不会自动检测主键是否冲突, 即便已存在相同主键也会添加进去
|
public XSIndex addExdata(string $data, bool $check_file=true)
| ||
| $data | string | 要提交的命令封包数据, 或存储命令封包的文件路径, 编码必须已经是 UTF-8 |
| $check_file | bool | 是否检测参数为文件的情况 |
| {return} | XSIndex | 返回自身对象以支持串接操作 |
public function addExdata($data, $check_file = true)
{
if (strlen($data) < 255 && $check_file
&& file_exists($data) && ($data = file_get_contents($data)) === false) {
throw new XSException('Failed to read exdata from file');
}
// try to check allowed (BUG: check the first cmd only):
// XS_CMD_IMPORT_HEADER, XS_CMD_INDEX_REQUEST, XS_CMD_INDEX_REMOVE, XS_CMD_INDEX_EXDATA
$first = ord(substr($data, 0, 1));
if ($first != XS_CMD_IMPORT_HEADER
&& $first != XS_CMD_INDEX_REQUEST && $first != XS_CMD_INDEX_SYNONYMS
&& $first != XS_CMD_INDEX_REMOVE && $first != XS_CMD_INDEX_EXDATA) {
throw new XSException('Invalid start command of exdata (CMD:' . $first . ')');
}
// create cmd & execute it
$cmd = array('cmd' => XS_CMD_INDEX_EXDATA, 'buf' => $data);
$this->execCommand($cmd, XS_CMD_OK_RQST_FINISHED);
return $this;
}
批量提交索引命令封包数据 把多个命令封包内容连续保存为文件或变量, 然后一次性提交以减少网络开销提升性能
|
public XSServer addServer(string $conn)
| ||
| $conn | string | 索引服务端连接参数 |
| {return} | XSServer | |
public function addServer($conn)
{
$srv = new XSServer($conn, $this->xs);
self::$_adds[] = $srv;
return $srv;
}
增加一个同步索引服务器
|
public XSIndex addSynonym(string $raw, string $synonym)
| ||
| $raw | string | 需要同义的原词, 英文词汇支持用空格分开多个单词并强制被转换为小写 |
| $synonym | string | 同义词条, 最小语素, 勿带空格等分隔符 |
| {return} | XSIndex | 返回自身对象以支持串接操作 |
public function addSynonym($raw, $synonym)
{
$raw = strval($raw);
$synonym = strval($synonym);
if ($raw !== '' && $synonym !== '') {
$cmd = new XSCommand(XS_CMD_INDEX_SYNONYMS, XS_CMD_INDEX_SYNONYMS_ADD, 0, $raw, $synonym);
if ($this->_bufSize > 0) {
$this->appendBuffer(strval($cmd));
} else {
$this->execCommand($cmd, XS_CMD_OK_RQST_FINISHED);
}
}
return $this;
}
添加同义词
|
public XSIndex beginRebuild()
| ||
| {return} | XSIndex | 返回自身对象以支持串接操作 |
public function beginRebuild()
{
$this->execCommand(array('cmd' => XS_CMD_INDEX_REBUILD, 'arg1' => 0), XS_CMD_OK_DB_REBUILD);
$this->_rebuild = true;
return $this;
}
开始重建索引 此后所有的索引更新指令将写到临时库, 而不是当前搜索库, 重建完成后调用 endRebuild 实现平滑重建索引, 重建过程仍可搜索旧的索引库, 如直接用 clean 清空数据, 则会导致重建过程搜索到不全的数据
|
public XSIndex clean()
| ||
| {return} | XSIndex | 返回自身对象以支持串接操作 |
public function clean()
{
$this->execCommand(XS_CMD_INDEX_CLEAN_DB, XS_CMD_OK_DB_CLEAN);
return $this;
}
完全清空索引数据 如果当前数据库处于重建过程中将禁止清空
|
public void close($ioerr=false)
| ||
| $ioerr | ||
public function close($ioerr = false)
{
$this->closeBuffer();
parent::close($ioerr);
}
关闭索引服务端连接
|
public XSIndex closeBuffer()
| ||
| {return} | XSIndex | 返回自身对象以支持串接操作 |
public function closeBuffer()
{
return $this->openBuffer(0);
}
提交所有指令并关闭缓冲区 若未曾打开缓冲区, 调用本方法是无意义的
|
public XSIndex del(mixed $term, string $field=NULL)
| ||
| $term | mixed | 单个主键或指定字段的索引词, 或多个组成的数组, 编码与 xs 默认字符集一致 |
| $field | string | 索引词所属的字段名称, 默认不指定则为主键字段 (类型为ID) |
| {return} | XSIndex | 返回自身对象以支持串接操作 |
public function del($term, $field = null)
{
// get field
$field = $field === null ? $this->xs->getFieldId() : $this->xs->getField($field);
// get commands
$cmds = array();
$terms = is_array($term) ? array_unique($term) : array($term);
$terms = XS::convert($terms, 'UTF-8', $this->xs->getDefaultCharset());
foreach ($terms as $term) {
$cmds[] = new XSCommand(XS_CMD_INDEX_REMOVE, 0, $field->vno, strtolower($term));
}
// combine multi commands into exdata
if ($this->_bufSize > 0) {
$this->appendBuffer(implode('', $cmds));
} elseif (count($cmds) == 1) {
$this->execCommand($cmds[0], XS_CMD_OK_RQST_FINISHED);
} else {
$cmd = array('cmd' => XS_CMD_INDEX_EXDATA, 'buf' => implode('', $cmds));
$this->execCommand($cmd, XS_CMD_OK_RQST_FINISHED);
}
return $this;
}
删除索引中的数据
$index->del('123'); // 删除主键为 123 的记录
$index->del(array('123', '789', '456')); // 删除主键为 123, 789, 456 的记录
$index->del('abc', 'field'); // 删除字段 field 上带有索引词 abc 的所有记录
$index->del(array('abc', 'def'), 'field'); // 删除字段 field 上带有索引词 abc 或 def 的所有记录
|
public XSIndex delSynonym(string $raw, string $synonym=NULL)
| ||
| $raw | string | 需要同义的原词, 英文词汇支持用空格分开多个单词并强制被转换为小写 |
| $synonym | string | 要删除的同义词条, 默认 null 表示删除原词下的所有同义词 |
| {return} | XSIndex | 返回自身对象以支持串接操作 |
public function delSynonym($raw, $synonym = null)
{
$raw = strval($raw);
$synonym = $synonym === null ? '' : strval($synonym);
if ($raw !== '') {
$cmd = new XSCommand(XS_CMD_INDEX_SYNONYMS, XS_CMD_INDEX_SYNONYMS_DEL, 0, $raw, $synonym);
if ($this->_bufSize > 0) {
$this->appendBuffer(strval($cmd));
} else {
$this->execCommand($cmd, XS_CMD_OK_RQST_FINISHED);
}
}
return $this;
}
删除某个同义词
|
public XSIndex endRebuild()
| ||
| {return} | XSIndex | 返回自身对象以支持串接操作 |
public function endRebuild()
{
if ($this->_rebuild === true) {
$this->_rebuild = false;
$this->execCommand(array('cmd' => XS_CMD_INDEX_REBUILD, 'arg1' => 1), XS_CMD_OK_DB_REBUILD);
}
return $this;
}
完成并关闭重建索引 重建完成后调用, 用重建好的索引数据代替旧的索引数据
|
public void execCommand($cmd, $res_arg=0, $res_cmd=128)
| ||
| $cmd | ||
| $res_arg | ||
| $res_cmd | ||
public function execCommand($cmd, $res_arg = XS_CMD_NONE, $res_cmd = XS_CMD_OK)
{
$res = parent::execCommand($cmd, $res_arg, $res_cmd);
foreach (self::$_adds as $srv) {
$srv->execCommand($cmd, $res_arg, $res_cmd);
}
return $res;
}
执行服务端指令并获取返回值 重写此方法是为了同步到额外增加的多个索引服务端
|
public bool flushIndex()
| ||
| {return} | bool | 刷新成功返回 true, 失败则返回 false |
public function flushIndex()
{
try {
$this->execCommand(XS_CMD_INDEX_COMMIT, XS_CMD_OK_DB_COMMITED);
} catch (XSException $e) {
if ($e->getCode() === XS_CMD_ERR_BUSY || $e->getCode() === XS_CMD_ERR_RUNNING) {
return false;
}
throw $e;
}
return true;
}
强制刷新服务端的当前库的索引缓存
|
public bool flushLogging()
| ||
| {return} | bool | 刷新成功返回 true, 失败则返回 false |
public function flushLogging()
{
try {
$this->execCommand(XS_CMD_FLUSH_LOGGING, XS_CMD_OK_LOG_FLUSHED);
} catch (XSException $e) {
if ($e->getCode() === XS_CMD_ERR_BUSY) {
return false;
}
throw $e;
}
return true;
}
强制刷新服务端当前项目的搜索日志
|
public string getCustomDict()
| ||
| {return} | string | 自定义词库内容 |
public function getCustomDict()
{
$res = $this->execCommand(XS_CMD_INDEX_USER_DICT, XS_CMD_OK_INFO);
return $res->buf;
}
获取自定义词典内容
|
public int getScwsMulti()
| ||
| {return} | int | 返回当前库的分词复合等级 |
public function getScwsMulti()
{
$cmd = array('cmd' => XS_CMD_SEARCH_SCWS_GET, 'arg1' => XS_CMD_SCWS_GET_MULTI);
$res = $this->execCommand($cmd, XS_CMD_OK_INFO);
return intval($res->buf);
}
获取当前索引库的分词复合等级
|
public XSIndex openBuffer(int $size=4)
| ||
| $size | int | 缓冲区大小, 单位: MB 默认为 4MB |
| {return} | XSIndex | 返回自身对象以支持串接操作 |
public function openBuffer($size = 4)
{
if ($this->_buf !== '') {
$this->addExdata($this->_buf, false);
}
$this->_bufSize = intval($size) << 20;
$this->_buf = '';
return $this;
}
开启索引命令提交缓冲区 为优化网络性能, 有必要先将本地提交的 add/update/del 等索引变动指令缓存下来, 当总大小达到参数指定的 size 时或调用 closeBuffer 时再真正提交到服务器 注意: 此举常用于需要大批量更新索引时, 此外重复调用本函数是无必要的
|
public void setCustomDict(string $content)
| ||
| $content | string | 新的词典内容 |
public function setCustomDict($content)
{
$cmd = array('cmd' => XS_CMD_INDEX_USER_DICT, 'arg1' => 1, 'buf' => $content);
$this->execCommand($cmd, XS_CMD_OK_DICT_SAVED);
}
设置自定义词典内容
|
public XSIndex setDb(string $name)
| ||
| $name | string | 数据库名称 |
| {return} | XSIndex | 返回自身对象以支持串接操作 |
public function setDb($name)
{
$this->execCommand(array('cmd' => XS_CMD_INDEX_SET_DB, 'buf' => $name), XS_CMD_OK_DB_CHANGED);
return $this;
}
更改存放索引数据的目录 默认索引数据保存到服务器上的 db 目录, 通过此方法修改数据目录名
|
public XSIndex setScwsMulti(int $level)
| ||
| $level | int | 要设置的分词复合等级 |
| {return} | XSIndex | 返回自身对象以支持串接操作 |
public function setScwsMulti($level)
{
$level = intval($level);
if ($level >= 0 && $level < 16) {
$cmd = array('cmd' => XS_CMD_SEARCH_SCWS_SET, 'arg1' => XS_CMD_SCWS_SET_MULTI, 'arg2' => $level);
$this->execCommand($cmd);
}
return $this;
}
设置当前索引库的分词复合等级 复合等级是 scws 分词粒度控制的一个重要参数, 是长词细分处理依据, 默认为 3, 值范围 0~15 注意: 这个设置仅直对当前索引库有效, 多次调用设置值被覆盖仅最后那次设置有效, 而且仅对设置之后提交的索引数据起作用, 如需对以前的索引数据生效请重建索引.
|
public XSIndex stopRebuild()
| ||
| {return} | XSIndex | 返回自身对象以支持串接操作 |
public function stopRebuild()
{
try {
$this->execCommand(array('cmd' => XS_CMD_INDEX_REBUILD, 'arg1' => 2), XS_CMD_OK_DB_REBUILD);
$this->_rebuild = false;
} catch (XSException $e) {
if ($e->getCode() !== XS_CMD_ERR_WRONGPLACE) {
throw $e;
}
}
return $this;
}
中止索引重建 丢弃重建临时库的所有数据, 恢复成当前搜索库, 主要用于偶尔重建意外中止的情况
|
public XSIndex update(XSDocument $doc, bool $add=false)
| ||
| $doc | XSDocument | |
| $add | bool | 是否为新增文档, 已有数据中不存在同一主键的其它数据 |
| {return} | XSIndex | 返回自身对象以支持串接操作 |
public function update(XSDocument $doc, $add = false)
{
// before submit
if ($doc->beforeSubmit($this) === false) {
return $this;
}
// check primary key of document
$fid = $this->xs->getFieldId();
$key = $doc->f($fid);
if ($key === null || $key === '') {
throw new XSException('Missing value of primary key (FIELD:' . $fid . ')');
}
// request cmd
$cmd = new XSCommand(XS_CMD_INDEX_REQUEST, XS_CMD_INDEX_REQUEST_ADD);
if ($add !== true) {
$cmd->arg1 = XS_CMD_INDEX_REQUEST_UPDATE;
$cmd->arg2 = $fid->vno;
$cmd->buf = $key;
}
$cmds = array($cmd);
// document cmds
foreach ($this->xs->getAllFields() as $field) /* @var $field XSFieldMeta */ {
// value
if (($value = $doc->f($field)) !== null) {
$varg = $field->isNumeric() ? XS_CMD_VALUE_FLAG_NUMERIC : 0;
$value = $field->val($value);
if (!$field->hasCustomTokenizer()) {
// internal tokenizer
$wdf = $field->weight | ($field->withPos() ? XS_CMD_INDEX_FLAG_WITHPOS : 0);
if ($field->hasIndexMixed()) {
$cmds[] = new XSCommand(XS_CMD_DOC_INDEX, $wdf, XSFieldScheme::MIXED_VNO, $value);
}
if ($field->hasIndexSelf()) {
$wdf |= $field->isNumeric() ? 0 : XS_CMD_INDEX_FLAG_SAVEVALUE;
$cmds[] = new XSCommand(XS_CMD_DOC_INDEX, $wdf, $field->vno, $value);
}
// add value
if (!$field->hasIndexSelf() || $field->isNumeric()) {
$cmds[] = new XSCommand(XS_CMD_DOC_VALUE, $varg, $field->vno, $value);
}
} else {
// add index
if ($field->hasIndex()) {
$terms = $field->getCustomTokenizer()->getTokens($value, $doc);
// self: [bool term, NOT weight, NOT stem, NOT pos]
if ($field->hasIndexSelf()) {
$wdf = $field->isBoolIndex() ? 1 : ($field->weight | XS_CMD_INDEX_FLAG_CHECKSTEM);
foreach ($terms as $term) {
if (strlen($term) > 200) {
continue;
}
$term = strtolower($term);
$cmds[] = new XSCommand(XS_CMD_DOC_TERM, $wdf, $field->vno, $term);
}
}
// mixed: [use default tokenizer]
if ($field->hasIndexMixed()) {
$mtext = implode(' ', $terms);
$cmds[] = new XSCommand(XS_CMD_DOC_INDEX, $field->weight, XSFieldScheme::MIXED_VNO, $mtext);
}
}
// add value
$cmds[] = new XSCommand(XS_CMD_DOC_VALUE, $varg, $field->vno, $value);
}
}
// process add terms
if (($terms = $doc->getAddTerms($field)) !== null) {
// ignore weight for bool index
$wdf1 = $field->isBoolIndex() ? 0 : XS_CMD_INDEX_FLAG_CHECKSTEM;
foreach ($terms as $term => $wdf) {
$term = strtolower($term);
if (strlen($term) > 200) {
continue;
}
$wdf2 = $field->isBoolIndex() ? 1 : $wdf * $field->weight;
while ($wdf2 > XSFieldMeta::MAX_WDF) {
$cmds[] = new XSCommand(XS_CMD_DOC_TERM, $wdf1 | XSFieldMeta::MAX_WDF, $field->vno, $term);
$wdf2 -= XSFieldMeta::MAX_WDF;
}
$cmds[] = new XSCommand(XS_CMD_DOC_TERM, $wdf1 | $wdf2, $field->vno, $term);
}
}
// process add text
if (($text = $doc->getAddIndex($field)) !== null) {
if (!$field->hasCustomTokenizer()) {
$wdf = $field->weight | ($field->withPos() ? XS_CMD_INDEX_FLAG_WITHPOS : 0);
$cmds[] = new XSCommand(XS_CMD_DOC_INDEX, $wdf, $field->vno, $text);
} else {
// NOT pos
$wdf = $field->isBoolIndex() ? 1 : ($field->weight | XS_CMD_INDEX_FLAG_CHECKSTEM);
$terms = $field->getCustomTokenizer()->getTokens($text, $doc);
foreach ($terms as $term) {
if (strlen($term) > 200) {
continue;
}
$term = strtolower($term);
$cmds[] = new XSCommand(XS_CMD_DOC_TERM, $wdf, $field->vno, $term);
}
}
}
}
// submit cmd
$cmds[] = new XSCommand(XS_CMD_INDEX_SUBMIT);
// execute cmd
if ($this->_bufSize > 0) {
$this->appendBuffer(implode('', $cmds));
} else {
for ($i = 0; $i < count($cmds) - 1; $i++) {
$this->execCommand($cmds[$i]);
}
$this->execCommand($cmds[$i], XS_CMD_OK_RQST_FINISHED);
}
// after submit
$doc->afterSubmit($this);
return $this;
}
更新索引文档 该方法相当于先根据主键删除已存在的旧文档, 然后添加该文档 如果你能明确认定是新文档, 则建议使用 add
| 包 | XS |
|---|---|
| 继承关系 | class XSIndex » XSServer » XSComponent |
| 版本 | 1.0.0 |
| 源代码 | sdk/php/lib/XSIndex.class.php |
| 名称 | 类型 | 描述 | 定义于 |
|---|---|---|---|
| connString | string | 连接字符串 | XSServer |
| customDict | string | 获取自定义词典内容 | XSIndex |
| project | string | 获取当前项目名称 | XSServer |
| respond | XSCommand | 从服务器读取响应指令 | XSServer |
| scwsMulti | int | 获取当前索引库的分词复合等级 | XSIndex |
| socket | mixed | 获取连接资源描述符 | XSServer |
| xs | XS | 服务端关联的 XS 对象 | XSServer |
| 名称 | 类型 | 描述 | 定义于 |
|---|---|---|---|
| _conn | XSServer | ||
| _flag | XSServer | ||
| _project | XSServer | ||
| _sendBuffer | XSServer | ||
| _sock | XSServer |
| 名称 | 描述 | 定义于 |
|---|---|---|
| __construct() | 构造函数, 打开连接 | XSServer |
| __destruct() | 析构函数 | XSIndex |
| __get() | 魔术方法 __get | XSComponent |
| __isset() | 魔术方法 __isset | XSComponent |
| __set() | 魔术方法 __set | XSComponent |
| __unset() | 魔术方法 __unset | XSComponent |
| add() | 添加文档到索引中 | XSIndex |
| addExdata() | 批量提交索引命令封包数据 | XSIndex |
| addServer() | 增加一个同步索引服务器 | XSIndex |
| addSynonym() | 添加同义词 | XSIndex |
| beginRebuild() | 开始重建索引 | XSIndex |
| clean() | 完全清空索引数据 | XSIndex |
| close() | 关闭索引服务端连接 | XSIndex |
| closeBuffer() | 提交所有指令并关闭缓冲区 | XSIndex |
| del() | 删除索引中的数据 | XSIndex |
| delSynonym() | 删除某个同义词 | XSIndex |
| endRebuild() | 完成并关闭重建索引 | XSIndex |
| execCommand() | 执行服务端指令并获取返回值 | XSIndex |
| flushIndex() | 强制刷新服务端的当前库的索引缓存 | XSIndex |
| flushLogging() | 强制刷新服务端当前项目的搜索日志 | XSIndex |
| getConnString() | Returns 连接字符串 | XSServer |
| getCustomDict() | 获取自定义词典内容 | XSIndex |
| getProject() | 获取当前项目名称 | XSServer |
| getRespond() | 从服务器读取响应指令 | XSServer |
| getScwsMulti() | 获取当前索引库的分词复合等级 | XSIndex |
| getSocket() | 获取连接资源描述符 | XSServer |
| hasRespond() | 判断服务端是否有可读数据 | XSServer |
| open() | 打开服务端连接 | XSServer |
| openBuffer() | 开启索引命令提交缓冲区 | XSIndex |
| reopen() | 重新打开连接 | XSServer |
| sendCommand() | 往服务器直接发送指令 (无缓存) | XSServer |
| setCustomDict() | 设置自定义词典内容 | XSIndex |
| setDb() | 更改存放索引数据的目录 | XSIndex |
| setProject() | 设置当前项目 | XSServer |
| setScwsMulti() | 设置当前索引库的分词复合等级 | XSIndex |
| setTimeout() | 设置服务端超时秒数 | XSServer |
| stopRebuild() | 中止索引重建 | XSIndex |
| update() | 更新索引文档 | XSIndex |
| 名称 | 描述 | 定义于 |
|---|---|---|
| check() | 检测服务端的连接情况 | XSServer |
| connect() | 连接服务端 | XSServer |
| read() | 读取数据 | XSServer |
| write() | 写入数据 | XSServer |
获取自定义词典内容
获取当前索引库的分词复合等级
|
public void __destruct()
|
public function __destruct()
{
if ($this->_rebuild === true) {
try {
$this->endRebuild();
} catch (Exception $e) {
}
}
foreach (self::$_adds as $srv) {
$srv->close();
}
self::$_adds = array();
parent::__destruct();
}
析构函数 在此自动关闭开启的 rebuild
|
public XSIndex add(XSDocument $doc)
| ||
| $doc | XSDocument | |
| {return} | XSIndex | 返回自身对象以支持串接操作 |
public function add(XSDocument $doc)
{
return $this->update($doc, true);
}
添加文档到索引中 特别要注意的是: 系统不会自动检测主键是否冲突, 即便已存在相同主键也会添加进去
|
public XSIndex addExdata(string $data, bool $check_file=true)
| ||
| $data | string | 要提交的命令封包数据, 或存储命令封包的文件路径, 编码必须已经是 UTF-8 |
| $check_file | bool | 是否检测参数为文件的情况 |
| {return} | XSIndex | 返回自身对象以支持串接操作 |
public function addExdata($data, $check_file = true)
{
if (strlen($data) < 255 && $check_file
&& file_exists($data) && ($data = file_get_contents($data)) === false) {
throw new XSException('Failed to read exdata from file');
}
// try to check allowed (BUG: check the first cmd only):
// XS_CMD_IMPORT_HEADER, XS_CMD_INDEX_REQUEST, XS_CMD_INDEX_REMOVE, XS_CMD_INDEX_EXDATA
$first = ord(substr($data, 0, 1));
if ($first != XS_CMD_IMPORT_HEADER
&& $first != XS_CMD_INDEX_REQUEST && $first != XS_CMD_INDEX_SYNONYMS
&& $first != XS_CMD_INDEX_REMOVE && $first != XS_CMD_INDEX_EXDATA) {
throw new XSException('Invalid start command of exdata (CMD:' . $first . ')');
}
// create cmd & execute it
$cmd = array('cmd' => XS_CMD_INDEX_EXDATA, 'buf' => $data);
$this->execCommand($cmd, XS_CMD_OK_RQST_FINISHED);
return $this;
}
批量提交索引命令封包数据 把多个命令封包内容连续保存为文件或变量, 然后一次性提交以减少网络开销提升性能
|
public XSServer addServer(string $conn)
| ||
| $conn | string | 索引服务端连接参数 |
| {return} | XSServer | |
public function addServer($conn)
{
$srv = new XSServer($conn, $this->xs);
self::$_adds[] = $srv;
return $srv;
}
增加一个同步索引服务器
|
public XSIndex addSynonym(string $raw, string $synonym)
| ||
| $raw | string | 需要同义的原词, 英文词汇支持用空格分开多个单词并强制被转换为小写 |
| $synonym | string | 同义词条, 最小语素, 勿带空格等分隔符 |
| {return} | XSIndex | 返回自身对象以支持串接操作 |
public function addSynonym($raw, $synonym)
{
$raw = strval($raw);
$synonym = strval($synonym);
if ($raw !== '' && $synonym !== '') {
$cmd = new XSCommand(XS_CMD_INDEX_SYNONYMS, XS_CMD_INDEX_SYNONYMS_ADD, 0, $raw, $synonym);
if ($this->_bufSize > 0) {
$this->appendBuffer(strval($cmd));
} else {
$this->execCommand($cmd, XS_CMD_OK_RQST_FINISHED);
}
}
return $this;
}
添加同义词
|
public XSIndex beginRebuild()
| ||
| {return} | XSIndex | 返回自身对象以支持串接操作 |
public function beginRebuild()
{
$this->execCommand(array('cmd' => XS_CMD_INDEX_REBUILD, 'arg1' => 0), XS_CMD_OK_DB_REBUILD);
$this->_rebuild = true;
return $this;
}
开始重建索引 此后所有的索引更新指令将写到临时库, 而不是当前搜索库, 重建完成后调用 endRebuild 实现平滑重建索引, 重建过程仍可搜索旧的索引库, 如直接用 clean 清空数据, 则会导致重建过程搜索到不全的数据
|
public XSIndex clean()
| ||
| {return} | XSIndex | 返回自身对象以支持串接操作 |
public function clean()
{
$this->execCommand(XS_CMD_INDEX_CLEAN_DB, XS_CMD_OK_DB_CLEAN);
return $this;
}
完全清空索引数据 如果当前数据库处于重建过程中将禁止清空
|
public void close($ioerr=false)
| ||
| $ioerr | ||
public function close($ioerr = false)
{
$this->closeBuffer();
parent::close($ioerr);
}
关闭索引服务端连接
|
public XSIndex closeBuffer()
| ||
| {return} | XSIndex | 返回自身对象以支持串接操作 |
public function closeBuffer()
{
return $this->openBuffer(0);
}
提交所有指令并关闭缓冲区 若未曾打开缓冲区, 调用本方法是无意义的
|
public XSIndex del(mixed $term, string $field=NULL)
| ||
| $term | mixed | 单个主键或指定字段的索引词, 或多个组成的数组, 编码与 xs 默认字符集一致 |
| $field | string | 索引词所属的字段名称, 默认不指定则为主键字段 (类型为ID) |
| {return} | XSIndex | 返回自身对象以支持串接操作 |
public function del($term, $field = null)
{
// get field
$field = $field === null ? $this->xs->getFieldId() : $this->xs->getField($field);
// get commands
$cmds = array();
$terms = is_array($term) ? array_unique($term) : array($term);
$terms = XS::convert($terms, 'UTF-8', $this->xs->getDefaultCharset());
foreach ($terms as $term) {
$cmds[] = new XSCommand(XS_CMD_INDEX_REMOVE, 0, $field->vno, strtolower($term));
}
// combine multi commands into exdata
if ($this->_bufSize > 0) {
$this->appendBuffer(implode('', $cmds));
} elseif (count($cmds) == 1) {
$this->execCommand($cmds[0], XS_CMD_OK_RQST_FINISHED);
} else {
$cmd = array('cmd' => XS_CMD_INDEX_EXDATA, 'buf' => implode('', $cmds));
$this->execCommand($cmd, XS_CMD_OK_RQST_FINISHED);
}
return $this;
}
删除索引中的数据
$index->del('123'); // 删除主键为 123 的记录
$index->del(array('123', '789', '456')); // 删除主键为 123, 789, 456 的记录
$index->del('abc', 'field'); // 删除字段 field 上带有索引词 abc 的所有记录
$index->del(array('abc', 'def'), 'field'); // 删除字段 field 上带有索引词 abc 或 def 的所有记录
|
public XSIndex delSynonym(string $raw, string $synonym=NULL)
| ||
| $raw | string | 需要同义的原词, 英文词汇支持用空格分开多个单词并强制被转换为小写 |
| $synonym | string | 要删除的同义词条, 默认 null 表示删除原词下的所有同义词 |
| {return} | XSIndex | 返回自身对象以支持串接操作 |
public function delSynonym($raw, $synonym = null)
{
$raw = strval($raw);
$synonym = $synonym === null ? '' : strval($synonym);
if ($raw !== '') {
$cmd = new XSCommand(XS_CMD_INDEX_SYNONYMS, XS_CMD_INDEX_SYNONYMS_DEL, 0, $raw, $synonym);
if ($this->_bufSize > 0) {
$this->appendBuffer(strval($cmd));
} else {
$this->execCommand($cmd, XS_CMD_OK_RQST_FINISHED);
}
}
return $this;
}
删除某个同义词
|
public XSIndex endRebuild()
| ||
| {return} | XSIndex | 返回自身对象以支持串接操作 |
public function endRebuild()
{
if ($this->_rebuild === true) {
$this->_rebuild = false;
$this->execCommand(array('cmd' => XS_CMD_INDEX_REBUILD, 'arg1' => 1), XS_CMD_OK_DB_REBUILD);
}
return $this;
}
完成并关闭重建索引 重建完成后调用, 用重建好的索引数据代替旧的索引数据
|
public void execCommand($cmd, $res_arg=0, $res_cmd=128)
| ||
| $cmd | ||
| $res_arg | ||
| $res_cmd | ||
public function execCommand($cmd, $res_arg = XS_CMD_NONE, $res_cmd = XS_CMD_OK)
{
$res = parent::execCommand($cmd, $res_arg, $res_cmd);
foreach (self::$_adds as $srv) {
$srv->execCommand($cmd, $res_arg, $res_cmd);
}
return $res;
}
执行服务端指令并获取返回值 重写此方法是为了同步到额外增加的多个索引服务端
|
public bool flushIndex()
| ||
| {return} | bool | 刷新成功返回 true, 失败则返回 false |
public function flushIndex()
{
try {
$this->execCommand(XS_CMD_INDEX_COMMIT, XS_CMD_OK_DB_COMMITED);
} catch (XSException $e) {
if ($e->getCode() === XS_CMD_ERR_BUSY || $e->getCode() === XS_CMD_ERR_RUNNING) {
return false;
}
throw $e;
}
return true;
}
强制刷新服务端的当前库的索引缓存
|
public bool flushLogging()
| ||
| {return} | bool | 刷新成功返回 true, 失败则返回 false |
public function flushLogging()
{
try {
$this->execCommand(XS_CMD_FLUSH_LOGGING, XS_CMD_OK_LOG_FLUSHED);
} catch (XSException $e) {
if ($e->getCode() === XS_CMD_ERR_BUSY) {
return false;
}
throw $e;
}
return true;
}
强制刷新服务端当前项目的搜索日志
|
public string getCustomDict()
| ||
| {return} | string | 自定义词库内容 |
public function getCustomDict()
{
$res = $this->execCommand(XS_CMD_INDEX_USER_DICT, XS_CMD_OK_INFO);
return $res->buf;
}
获取自定义词典内容
|
public int getScwsMulti()
| ||
| {return} | int | 返回当前库的分词复合等级 |
public function getScwsMulti()
{
$cmd = array('cmd' => XS_CMD_SEARCH_SCWS_GET, 'arg1' => XS_CMD_SCWS_GET_MULTI);
$res = $this->execCommand($cmd, XS_CMD_OK_INFO);
return intval($res->buf);
}
获取当前索引库的分词复合等级
|
public XSIndex openBuffer(int $size=4)
| ||
| $size | int | 缓冲区大小, 单位: MB 默认为 4MB |
| {return} | XSIndex | 返回自身对象以支持串接操作 |
public function openBuffer($size = 4)
{
if ($this->_buf !== '') {
$this->addExdata($this->_buf, false);
}
$this->_bufSize = intval($size) << 20;
$this->_buf = '';
return $this;
}
开启索引命令提交缓冲区 为优化网络性能, 有必要先将本地提交的 add/update/del 等索引变动指令缓存下来, 当总大小达到参数指定的 size 时或调用 closeBuffer 时再真正提交到服务器 注意: 此举常用于需要大批量更新索引时, 此外重复调用本函数是无必要的
|
public void setCustomDict(string $content)
| ||
| $content | string | 新的词典内容 |
public function setCustomDict($content)
{
$cmd = array('cmd' => XS_CMD_INDEX_USER_DICT, 'arg1' => 1, 'buf' => $content);
$this->execCommand($cmd, XS_CMD_OK_DICT_SAVED);
}
设置自定义词典内容
|
public XSIndex setDb(string $name)
| ||
| $name | string | 数据库名称 |
| {return} | XSIndex | 返回自身对象以支持串接操作 |
public function setDb($name)
{
$this->execCommand(array('cmd' => XS_CMD_INDEX_SET_DB, 'buf' => $name), XS_CMD_OK_DB_CHANGED);
return $this;
}
更改存放索引数据的目录 默认索引数据保存到服务器上的 db 目录, 通过此方法修改数据目录名
|
public XSIndex setScwsMulti(int $level)
| ||
| $level | int | 要设置的分词复合等级 |
| {return} | XSIndex | 返回自身对象以支持串接操作 |
public function setScwsMulti($level)
{
$level = intval($level);
if ($level >= 0 && $level < 16) {
$cmd = array('cmd' => XS_CMD_SEARCH_SCWS_SET, 'arg1' => XS_CMD_SCWS_SET_MULTI, 'arg2' => $level);
$this->execCommand($cmd);
}
return $this;
}
设置当前索引库的分词复合等级 复合等级是 scws 分词粒度控制的一个重要参数, 是长词细分处理依据, 默认为 3, 值范围 0~15 注意: 这个设置仅直对当前索引库有效, 多次调用设置值被覆盖仅最后那次设置有效, 而且仅对设置之后提交的索引数据起作用, 如需对以前的索引数据生效请重建索引.
|
public XSIndex stopRebuild()
| ||
| {return} | XSIndex | 返回自身对象以支持串接操作 |
public function stopRebuild()
{
try {
$this->execCommand(array('cmd' => XS_CMD_INDEX_REBUILD, 'arg1' => 2), XS_CMD_OK_DB_REBUILD);
$this->_rebuild = false;
} catch (XSException $e) {
if ($e->getCode() !== XS_CMD_ERR_WRONGPLACE) {
throw $e;
}
}
return $this;
}
中止索引重建 丢弃重建临时库的所有数据, 恢复成当前搜索库, 主要用于偶尔重建意外中止的情况
|
public XSIndex update(XSDocument $doc, bool $add=false)
| ||
| $doc | XSDocument | |
| $add | bool | 是否为新增文档, 已有数据中不存在同一主键的其它数据 |
| {return} | XSIndex | 返回自身对象以支持串接操作 |
public function update(XSDocument $doc, $add = false)
{
// before submit
if ($doc->beforeSubmit($this) === false) {
return $this;
}
// check primary key of document
$fid = $this->xs->getFieldId();
$key = $doc->f($fid);
if ($key === null || $key === '') {
throw new XSException('Missing value of primary key (FIELD:' . $fid . ')');
}
// request cmd
$cmd = new XSCommand(XS_CMD_INDEX_REQUEST, XS_CMD_INDEX_REQUEST_ADD);
if ($add !== true) {
$cmd->arg1 = XS_CMD_INDEX_REQUEST_UPDATE;
$cmd->arg2 = $fid->vno;
$cmd->buf = $key;
}
$cmds = array($cmd);
// document cmds
foreach ($this->xs->getAllFields() as $field) /* @var $field XSFieldMeta */ {
// value
if (($value = $doc->f($field)) !== null) {
$varg = $field->isNumeric() ? XS_CMD_VALUE_FLAG_NUMERIC : 0;
$value = $field->val($value);
if (!$field->hasCustomTokenizer()) {
// internal tokenizer
$wdf = $field->weight | ($field->withPos() ? XS_CMD_INDEX_FLAG_WITHPOS : 0);
if ($field->hasIndexMixed()) {
$cmds[] = new XSCommand(XS_CMD_DOC_INDEX, $wdf, XSFieldScheme::MIXED_VNO, $value);
}
if ($field->hasIndexSelf()) {
$wdf |= $field->isNumeric() ? 0 : XS_CMD_INDEX_FLAG_SAVEVALUE;
$cmds[] = new XSCommand(XS_CMD_DOC_INDEX, $wdf, $field->vno, $value);
}
// add value
if (!$field->hasIndexSelf() || $field->isNumeric()) {
$cmds[] = new XSCommand(XS_CMD_DOC_VALUE, $varg, $field->vno, $value);
}
} else {
// add index
if ($field->hasIndex()) {
$terms = $field->getCustomTokenizer()->getTokens($value, $doc);
// self: [bool term, NOT weight, NOT stem, NOT pos]
if ($field->hasIndexSelf()) {
$wdf = $field->isBoolIndex() ? 1 : ($field->weight | XS_CMD_INDEX_FLAG_CHECKSTEM);
foreach ($terms as $term) {
if (strlen($term) > 200) {
continue;
}
$term = strtolower($term);
$cmds[] = new XSCommand(XS_CMD_DOC_TERM, $wdf, $field->vno, $term);
}
}
// mixed: [use default tokenizer]
if ($field->hasIndexMixed()) {
$mtext = implode(' ', $terms);
$cmds[] = new XSCommand(XS_CMD_DOC_INDEX, $field->weight, XSFieldScheme::MIXED_VNO, $mtext);
}
}
// add value
$cmds[] = new XSCommand(XS_CMD_DOC_VALUE, $varg, $field->vno, $value);
}
}
// process add terms
if (($terms = $doc->getAddTerms($field)) !== null) {
// ignore weight for bool index
$wdf1 = $field->isBoolIndex() ? 0 : XS_CMD_INDEX_FLAG_CHECKSTEM;
foreach ($terms as $term => $wdf) {
$term = strtolower($term);
if (strlen($term) > 200) {
continue;
}
$wdf2 = $field->isBoolIndex() ? 1 : $wdf * $field->weight;
while ($wdf2 > XSFieldMeta::MAX_WDF) {
$cmds[] = new XSCommand(XS_CMD_DOC_TERM, $wdf1 | XSFieldMeta::MAX_WDF, $field->vno, $term);
$wdf2 -= XSFieldMeta::MAX_WDF;
}
$cmds[] = new XSCommand(XS_CMD_DOC_TERM, $wdf1 | $wdf2, $field->vno, $term);
}
}
// process add text
if (($text = $doc->getAddIndex($field)) !== null) {
if (!$field->hasCustomTokenizer()) {
$wdf = $field->weight | ($field->withPos() ? XS_CMD_INDEX_FLAG_WITHPOS : 0);
$cmds[] = new XSCommand(XS_CMD_DOC_INDEX, $wdf, $field->vno, $text);
} else {
// NOT pos
$wdf = $field->isBoolIndex() ? 1 : ($field->weight | XS_CMD_INDEX_FLAG_CHECKSTEM);
$terms = $field->getCustomTokenizer()->getTokens($text, $doc);
foreach ($terms as $term) {
if (strlen($term) > 200) {
continue;
}
$term = strtolower($term);
$cmds[] = new XSCommand(XS_CMD_DOC_TERM, $wdf, $field->vno, $term);
}
}
}
}
// submit cmd
$cmds[] = new XSCommand(XS_CMD_INDEX_SUBMIT);
// execute cmd
if ($this->_bufSize > 0) {
$this->appendBuffer(implode('', $cmds));
} else {
for ($i = 0; $i < count($cmds) - 1; $i++) {
$this->execCommand($cmds[$i]);
}
$this->execCommand($cmds[$i], XS_CMD_OK_RQST_FINISHED);
}
// after submit
$doc->afterSubmit($this);
return $this;
}
更新索引文档 该方法相当于先根据主键删除已存在的旧文档, 然后添加该文档 如果你能明确认定是新文档, 则建议使用 add
一条评论！
在调用了add方法后立马调用flushIndex()会出现该document被建立了两条索引了
请到论坛 登录 后刷新本页面！