Change location into the fulltext_plugin directory:

shell> cd fulltext_plugin

The plugin source file should include the header files that the plugin library needs. The plugin.h file is required, and the library might require other files as well. For example:

#include <stdlib.h>
#include <ctype.h>
#include <mysql/plugin.h>

Set up the plugin library file descriptor.

Every plugin library must include a library descriptor that must define two symbols:

If the server does not find these two symbols in a library, it does not accept it as a legal plugin library and rejects it with an error. This prevents use of a library for plugin purposes unless it was built specifically as a plugin library.

The standard (and most convenient) way to define the two required symbols is by using the mysql_declare_plugin and mysql_declare_plugin_end macros from the plugin.h file:

mysql_declare_plugin
 ... one or more plugin declarations here ...
mysql_declare_plugin_end;

For example, the library descriptor for a library that contains a single plugin named simple_parser looks like this:

mysql_declare_plugin
{
  MYSQL_FTPARSER_PLUGIN,      /* type                            */
  &simple_parser_descriptor,  /* descriptor                      */
  "simple_parser",            /* name                            */
  "Oracle Corporation",       /* author                          */
  "Simple Full-Text Parser",  /* description                     */
  PLUGIN_LICENSE_GPL,         /* plugin license                  */
  simple_parser_plugin_init,  /* init function (when loaded)     */
  simple_parser_plugin_deinit,/* deinit function (when unloaded) */
  0x0001,                     /* version                         */
  simple_status               /* status variables                */
}
mysql_declare_plugin_end;

For a full-text parser plugin, the type must be MYSQL_FTPARSER_PLUGIN. This is the value that identifies the plugin as being legal for use in a WITH PARSER clause when creating a FULLTEXT index. (No other plugin type is legal for this clause.)

The mysql_declare_plugin and mysql_declare_plugin_end macros are defined in plugin.h like this:

#ifndef MYSQL_DYNAMIC_PLUGIN
#define __MYSQL_DECLARE_PLUGIN(NAME, VERSION, PSIZE, DECLS)           \
int VERSION= MYSQL_PLUGIN_INTERFACE_VERSION;                          \
int PSIZE= sizeof(struct st_mysql_plugin);                            \
struct st_mysql_plugin DECLS[]= {
#else
#define __MYSQL_DECLARE_PLUGIN(NAME, VERSION, PSIZE, DECLS)           \
int _mysql_plugin_interface_version_= MYSQL_PLUGIN_INTERFACE_VERSION; \
int _mysql_sizeof_struct_st_plugin_= sizeof(struct st_mysql_plugin);  \
struct st_mysql_plugin _mysql_plugin_declarations_[]= {
#endif

#define mysql_declare_plugin(NAME) \
__MYSQL_DECLARE_PLUGIN(NAME, \
                 builtin_ ## NAME ## _plugin_interface_version, \
                 builtin_ ## NAME ## _sizeof_struct_st_plugin, \
                 builtin_ ## NAME ## _plugin)

#define mysql_declare_plugin_end ,{0,0,0,0,0,0,0,0,0}}

When the macros are used as just shown, they expand to the following code, which defines both of the required symbols (_mysql_plugin_interface_version_ and _mysql_plugin_declarations_):

int _mysql_plugin_interface_version_= MYSQL_PLUGIN_INTERFACE_VERSION;
struct st_mysql_plugin _mysql_plugin_declarations_[]= {
{
  MYSQL_FTPARSER_PLUGIN,      /* type                            */
  &simple_parser_descriptor,  /* descriptor                      */
  "simple_parser",            /* name                            */
  "Oracle Corporation",       /* author                          */
  "Simple Full-Text Parser",  /* description                     */
  PLUGIN_LICENSE_GPL,         /* plugin license                  */
  simple_parser_plugin_init,  /* init function (when loaded)     */
  simple_parser_plugin_deinit,/* deinit function (when unloaded) */
  0x0001,                     /* version                         */
  simple_status               /* status variables                */
}
  ,{0,0,0,0,0,0,00,0}
};

The preceding example declares a single plugin in the library descriptor, but it is possible to declare multiple plugins. List the declarations one after the other between mysql_declare_plugin and mysql_declare_plugin_end, separated by commas.

MySQL plugins can be written in C or C++ (or another language that can use C calling conventions). If you write a C++ plugin, one C++ feature that you should not use is nonconstant variables to initialize global structures. Members of structures such as the st_mysql_plugin structure should be initialized only with constant variables. The simple_parser descriptor shown earlier is allowable in a C++ plugin because it satisfies that requirement:

mysql_declare_plugin
{
  MYSQL_FTPARSER_PLUGIN,      /* type                            */
  &simple_parser_descriptor,  /* descriptor                      */
  "simple_parser",            /* name                            */
  "Oracle Corporation",       /* author                          */
  "Simple Full-Text Parser",  /* description                     */
  PLUGIN_LICENSE_GPL,         /* plugin license                  */
  simple_parser_plugin_init,  /* init function (when loaded)     */
  simple_parser_plugin_deinit,/* deinit function (when unloaded) */
  0x0001,                     /* version                         */
  simple_status               /* status variables                */
}
mysql_declare_plugin_end;

Here is another valid way to write the descriptor. It uses constant variables to indicate the plugin name, author, and description:

const char *simple_parser_name = "simple_parser";
const char *simple_parser_author = "Oracle Corporation";
const char *simple_parser_description = "Simple Full-Text Parser";

mysql_declare_plugin
{
  MYSQL_FTPARSER_PLUGIN,      /* type                            */
  &simple_parser_descriptor,  /* descriptor                      */
  simple_parser_name,         /* name                            */
  simple_parser_author,       /* author                          */
  simple_parser_description,  /* description                     */
  PLUGIN_LICENSE_GPL,         /* plugin license                  */
  simple_parser_plugin_init,  /* init function (when loaded)     */
  simple_parser_plugin_deinit,/* deinit function (when unloaded) */
  0x0001,                     /* version                         */
  simple_status               /* status variables                */
}
mysql_declare_plugin_end;

However, the following descriptor is invalid. It uses structure members to indicate the plugin name, author, and description, but structures are not considered constant initializers in C++:

typedef struct
{
  const char *name;
  const char *author;
  const char *description;
} plugin_info;

plugin_info parser_info = {
  "simple_parser",
  "Oracle Corporation",
  "Simple Full-Text Parser"
};

mysql_declare_plugin
{
  MYSQL_FTPARSER_PLUGIN,      /* type                            */
  &simple_parser_descriptor,  /* descriptor                      */
  parser_info.name,           /* name                            */
  parser_info.author,         /* author                          */
  parser_info.description,    /* description                     */
  PLUGIN_LICENSE_GPL,         /* plugin license                  */
  simple_parser_plugin_init,  /* init function (when loaded)     */
  simple_parser_plugin_deinit,/* deinit function (when unloaded) */
  0x0001,                     /* version                         */
  simple_status               /* status variables                */
}
mysql_declare_plugin_end;

Set up the plugin descriptor.

Each plugin declaration in the library descriptor points to a type-specific descriptor for the corresponding plugin. In the simple_parser declaration, that descriptor is indicated by &simple_parser_descriptor. The descriptor specifies the version number for the full-text plugin interface (as given by MYSQL_FTPARSER_INTERFACE_VERSION), and the plugin's parsing, initialization, and deinitialization functions:

static struct st_mysql_ftparser simple_parser_descriptor=
{
  MYSQL_FTPARSER_INTERFACE_VERSION, /* interface version      */
  simple_parser_parse,              /* parsing function       */
  simple_parser_init,               /* parser init function   */
  simple_parser_deinit              /* parser deinit function */
};

Set up the plugin interface functions.

The general plugin descriptor in the library descriptor names the initialization and deinitialization functions that the server should invoke when it loads and unloads the plugin. For simple_parser, these functions do nothing but return zero to indicate that they succeeded:

static int simple_parser_plugin_init(void)
{
  return(0);
}

static int simple_parser_plugin_deinit(void)
{
  return(0);
}

Because those functions do not actually do anything, you could omit them and specify 0 for each of them in the plugin declaration.

The type-specific plugin descriptor for simple_parser names the initialization, deinitialization, and parsing functions that the server invokes when the plugin is used. For simple_parser, the initialization and deinitialization functions do nothing:

static int simple_parser_init(MYSQL_FTPARSER_PARAM *param)
{
  return(0);
}

static int simple_parser_deinit(MYSQL_FTPARSER_PARAM *param)
{
  return(0);
}

Here too, because those functions do nothing, you could omit them and specify 0 for each of them in the plugin descriptor.

The main parsing function, simple_parser_parse(), acts as a replacement for the built-in full-text parser, so it needs to split text into words and pass each word to the server. The parsing function's first argument is a pointer to a structure that contains the parsing context. This structure has a doc member that points to the text to be parsed, and a length member that indicates how long the text is. The simple parsing done by the plugin considers nonempty runs of whitespace characters to be words, so it identifies words like this:

static int simple_parser_parse(MYSQL_FTPARSER_PARAM *param)
{
  char *end, *start, *docend= param->doc + param->length;

  for (end= start= param->doc;; end++)
  {
    if (end == docend)
    {
      if (end > start)
        add_word(param, start, end - start);
      break;
    }
    else if (isspace(*end))
    {
      if (end > start)
        add_word(param, start, end - start);
      start= end + 1;
    }
  }
  return(0);
}

As the parser finds each word, it invokes a function add_word() to pass the word to the server. add_word() is a helper function only; it is not part of the plugin interface. The parser passes the parsing context pointer to add_word(), as well as a pointer to the word and a length value:

static void add_word(MYSQL_FTPARSER_PARAM *param, char *word, size_t len)
{
  MYSQL_FTPARSER_BOOLEAN_INFO bool_info=
    { FT_TOKEN_WORD, 0, 0, 0, 0, ' ', 0 };

  param->mysql_add_word(param, word, len, &bool_info);
}

For boolean-mode parsing, add_word() fills in the members of the bool_info structure as described in Section 21.2.4.2.1, “Full-Text Parser Plugin Data Structures and Functions”.

Set up the status variables, if there are any. For the simple_parser plugin, the following status variable array sets up one status variable with a value that is static text, and another with a value that is stored in a long integer variable:

long number_of_calls= 0;

struct st_mysql_show_var simple_status[]=
{
  {"static", (char *)"just a static text", SHOW_CHAR},
  {"called", (char *)&number_of_calls,     SHOW_LONG},
  {0,0,0}
};

When the plugin is installed, the plugin name and the name value are joined with an underscore to form the name displayed by SHOW STATUS. For the array just shown, the resulting status variable names are simple_parser_static and simple_parser_called. This convention means that you can easily display the variables for a plugin using its name:

mysql> SHOW STATUS LIKE 'simple_parser%';
+----------------------+--------------------+
| Variable_name        | Value              |
+----------------------+--------------------+
| simple_parser_static | just a static text |
| simple_parser_called | 0                  |
+----------------------+--------------------+

Compile the plugin library as a shared library and install it in the plugin directory.

The procedure for compiling shared objects varies from system to system. If you build your library using the GNU autotools, libtool should be able to generate the correct compilation commands for your system. If the library is named mypluglib, you should end up with a shared object file that has a name something like libmypluglib.so. (The file name might have a different extension on your system.)

To use the autotools, you'll need to make a few changes to the configuration files at this point to enable the plugin to be compiled and installed. Assume that your MySQL distribution is installed at a base directory of /usr/local/mysql and that its header files are located in the include directory under the base directory.

Edit Makefile.am, which should look something like this:

#Makefile.am example for a plugin

pkgplugindir=$(libdir)/mysql/plugin
INCLUDES= -I$(top_builddir)/include -I$(top_srcdir)/include
#noinst_LTLIBRARIES= mypluglib.la
pkgplugin_LTLIBRARIES= mypluglib.la
mypluglib_la_SOURCES= plugin_example.c
mypluglib_la_LDFLAGS= -module -rpath $(pkgplugindir)
mypluglib_la_CFLAGS= -DMYSQL_DYNAMIC_PLUGIN

The mypluglib_la_CFLAGS line takes care of passing the -DMYSQL_DYNAMIC_PLUGIN flag to the compilation command.

Adjust the INCLUDES line to specify the path name to the installed MySQL header files. Edit it to look like this:

INCLUDES= -I/usr/local/mysql/include

Make sure that the noinst_LTLIBRARIES line is commented out or remove it. Make sure that the pkglib_LTLIBRARIES line is not commented out; it enables the make install command.

Set up the files needed for the configure command, invoke it, and run make:

shell> autoreconf --force --install --symlink
shell> ./configure --prefix=/usr/local/mysql
shell> make

The --prefix option to configure indicates the MySQL base directory under which the plugin should be installed. You can see what value to use for this option with SHOW VARIABLES:

mysql> SHOW VARIABLES LIKE 'basedir';
+---------------+------------------+
| Variable_name | Value            |
+---------------+------------------+
| base          | /usr/local/mysql |
+---------------+------------------+

The location of the plugin directory where you should install the library is given by the plugin_dir system variable. For example:

mysql> SHOW VARIABLES LIKE 'plugin_dir';
+---------------+-----------------------------------+
| Variable_name | Value                             |
+---------------+-----------------------------------+
| plugin_dir    | /usr/local/mysql/lib/mysql/plugin |
+---------------+-----------------------------------+

To install the plugin library, use make:

shell> make install

Verify that make install installed the plugin library in the proper directory. After installing it, make sure that the library permissions allow it to be executed by the server.

Register the plugin with the server.

The INSTALL PLUGIN statement causes the server to register the plugin in the plugin table and to load the plugin code from the library file. Use that statement to register simple_parser with the server, and then verify that the plugin is listed in the plugin table:

mysql> INSTALL PLUGIN simple_parser SONAME 'libmypluglib.so';
Query OK, 0 rows affected (0.00 sec)

mysql> SELECT * FROM mysql.plugin;
+---------------+-----------------+
| name          | dl              |
+---------------+-----------------+
| simple_parser | libmypluglib.so |
+---------------+-----------------+
1 row in set (0.00 sec)

For additional information about plugin loading, see Section 12.4.3.1, “Installing and Uninstalling Plugins”.

Try the plugin.

Create a table that contains a string column and associate the parser plugin with a FULLTEXT index on the column:

mysql> CREATE TABLE t (c VARCHAR(255),
    ->   FULLTEXT (c) WITH PARSER simple_parser);
Query OK, 0 rows affected (0.01 sec)

Insert some text into the table and try some searches. These should verify that the parser plugin treats all nonwhitespace characters as word characters:

mysql> INSERT INTO t VALUES
    ->   ('latin1_general_cs is a case-sensitive collation'),
    ->   ('I\'d like a case of oranges'),
    ->   ('this is sensitive information'),
    ->   ('another row'),
    ->   ('yet another row');
Query OK, 5 rows affected (0.02 sec)
Records: 5  Duplicates: 0  Warnings: 0

mysql> SELECT c FROM t;
+-------------------------------------------------+
| c                                               |
+-------------------------------------------------+
| latin1_general_cs is a case-sensitive collation |
| I'd like a case of oranges                      |
| this is sensitive information                   |
| another row                                     |
| yet another row                                 |
+-------------------------------------------------+
5 rows in set (0.00 sec)

mysql> SELECT MATCH(c) AGAINST('case') FROM t;
+--------------------------+
| MATCH(c) AGAINST('case') |
+--------------------------+
|                        0 |
|          1.2968142032623 |
|                        0 |
|                        0 |
|                        0 |
+--------------------------+
5 rows in set (0.00 sec)

mysql> SELECT MATCH(c) AGAINST('sensitive') FROM t;
+-------------------------------+
| MATCH(c) AGAINST('sensitive') |
+-------------------------------+
|                             0 |
|                             0 |
|               1.3253291845322 |
|                             0 |
|                             0 |
+-------------------------------+
5 rows in set (0.01 sec)

mysql> SELECT MATCH(c) AGAINST('case-sensitive') FROM t;
+------------------------------------+
| MATCH(c) AGAINST('case-sensitive') |
+------------------------------------+
|                    1.3109166622162 |
|                                  0 |
|                                  0 |
|                                  0 |
|                                  0 |
+------------------------------------+
5 rows in set (0.01 sec)

mysql> SELECT MATCH(c) AGAINST('I\'d') FROM t;
+--------------------------+
| MATCH(c) AGAINST('I\'d') |
+--------------------------+
|                        0 |
|          1.2968142032623 |
|                        0 |
|                        0 |
|                        0 |
+--------------------------+
5 rows in set (0.01 sec)