类
struct	ObPluginFTParser
	fulltext parser descriptor interface for domain index splitting a document into many tokenizations.return the version of this parser 更多...

宏定义
#define	OBP_FTPARSER_INTERFACE_VERSION OBP_MAKE_VERSION(0, 1, 0)
	full text parser interface version

#define	OBP_FTPARSER_INTERFACE_VERSION_0_2_0 OBP_MAKE_VERSION(0, 2, 0)

#define	OBP_FTPARSER_INTERFACE_VERSION_CURRENT OBP_FTPARSER_INTERFACE_VERSION_0_2_0
	current full text parser interface version

#define	OBP_REGISTER_FTPARSER(param, name, descriptor, description)

类型定义
typedef ObPluginDatum	ObPluginFTParserParamPtr
	full text parser add word flag

枚举
enum	ObPluginFTPaserAddWordFlag { OBP_FTPARSER_AWF_NONE = 0LL , OBP_FTPARSER_AWF_MIN_MAX_WORD = 1LL << 0 , OBP_FTPARSER_AWF_STOPWORD = 1LL << 1 , OBP_FTPARSER_AWF_CASEDOWN = 1LL << 2 , OBP_FTPARSER_AWF_GROUPBY_WORD = 1LL << 3 }

函数
OBP_PUBLIC_API uint64_t	obp_ftparser_parser_version (ObPluginFTParserParamPtr param)

OBP_PUBLIC_API const char *	obp_ftparser_fulltext (ObPluginFTParserParamPtr param)
	the `fulltext` is the text you should split it to tokens @NOTE the `fulltext` is not terminated by '\0'.

OBP_PUBLIC_API int64_t	obp_ftparser_fulltext_length (ObPluginFTParserParamPtr param)
	get the charsetinfo object from param

OBP_PUBLIC_API ObPluginCharsetInfoPtr	obp_ftparser_charset_info (ObPluginFTParserParamPtr param)

OBP_PUBLIC_API ObPluginParamPtr	obp_ftparser_plugin_param (ObPluginFTParserParamPtr param)
	get the plugin parameter through fulltext parser parameter

OBP_PUBLIC_API ObPluginDatum	obp_ftparser_user_data (ObPluginFTParserParamPtr param)
	The user data of fulltext parameter

OBP_PUBLIC_API void	obp_ftparser_set_user_data (ObPluginFTParserParamPtr param, ObPluginDatum user_data)
	set user data

OBP_PUBLIC_API int	obp_register_plugin_ftparser (ObPluginParamPtr param, const char name, ObPluginVersion version, ObPluginFTParser ftparser, int64_t ftparser_sizeof, const char *description)
	register fulltext parser plugin @NOTE use `OBP_REGISTER_FTPARSER` instead

详细描述

宏定义说明

◆ OBP_FTPARSER_INTERFACE_VERSION

#define OBP_FTPARSER_INTERFACE_VERSION OBP_MAKE_VERSION(0, 1, 0)

full text parser interface version

注解: this is the minimum version. You should add new version if you add new routines.

在文件 ob_plugin_ftparser.h 第 28 行定义.

◆ OBP_FTPARSER_INTERFACE_VERSION_0_2_0

#define OBP_FTPARSER_INTERFACE_VERSION_0_2_0 OBP_MAKE_VERSION(0, 2, 0)

在文件 ob_plugin_ftparser.h 第 30 行定义.

◆ OBP_FTPARSER_INTERFACE_VERSION_CURRENT

#define OBP_FTPARSER_INTERFACE_VERSION_CURRENT OBP_FTPARSER_INTERFACE_VERSION_0_2_0

current full text parser interface version

注解: you should change this value if you add some new routines in interface struct. full text parser parameter

在文件 ob_plugin_ftparser.h 第 36 行定义.

◆ OBP_REGISTER_FTPARSER

#define OBP_REGISTER_FTPARSER	(	param,
		name,
		descriptor,
		description )

值:

  obp_register_plugin_ftparser(param,                                  \
                               name,                                   \
                               OBP_FTPARSER_INTERFACE_VERSION_CURRENT, \
                               &descriptor,                            \
                               (int64_t)sizeof(descriptor),            \
                               description);

在文件 ob_plugin_ftparser.h 第 147 行定义.

类型定义说明

◆ ObPluginFTParserParamPtr

typedef ObPluginDatum ObPluginFTParserParamPtr

full text parser add word flag

在文件 ob_plugin_ftparser.h 第 43 行定义.

枚举类型说明

◆ ObPluginFTPaserAddWordFlag

enum ObPluginFTPaserAddWordFlag

枚举值
OBP_FTPARSER_AWF_NONE	filter words that are less than a minimum or greater than a maximum word length.
OBP_FTPARSER_AWF_MIN_MAX_WORD	filter by sotp word table.
OBP_FTPARSER_AWF_STOPWORD	convert characters from uppercase to lowercase.
OBP_FTPARSER_AWF_CASEDOWN	distinct and word aggregation
OBP_FTPARSER_AWF_GROUPBY_WORD

在文件 ob_plugin_ftparser.h 第 46 行定义.

函数说明

◆ obp_ftparser_charset_info()

OBP_PUBLIC_API ObPluginCharsetInfoPtr obp_ftparser_charset_info ( ObPluginFTParserParamPtr param )

◆ obp_ftparser_fulltext()

OBP_PUBLIC_API const char * obp_ftparser_fulltext ( ObPluginFTParserParamPtr param )

the fulltext is the text you should split it to tokens @NOTE the fulltext is not terminated by '\0'.

You can use obp_ftparser_fulltext_length to get the length. the length of fulltext

◆ obp_ftparser_fulltext_length()

OBP_PUBLIC_API int64_t obp_ftparser_fulltext_length ( ObPluginFTParserParamPtr param )

get the charsetinfo object from param

◆ obp_ftparser_parser_version()

OBP_PUBLIC_API uint64_t obp_ftparser_parser_version ( ObPluginFTParserParamPtr param )

◆ obp_ftparser_plugin_param()

OBP_PUBLIC_API ObPluginParamPtr obp_ftparser_plugin_param ( ObPluginFTParserParamPtr param )

get the plugin parameter through fulltext parser parameter

◆ obp_ftparser_set_user_data()

OBP_PUBLIC_API void obp_ftparser_set_user_data	(	ObPluginFTParserParamPtr	param,
		ObPluginDatum	user_data )

set user data

You can retrieve user data by obp_ftparser_user_data

◆ obp_ftparser_user_data()

OBP_PUBLIC_API ObPluginDatum obp_ftparser_user_data ( ObPluginFTParserParamPtr param )

The user data of fulltext parameter

User data is a pointer (void *) so that you can set it to anything you want.

◆ obp_register_plugin_ftparser()

OBP_PUBLIC_API int obp_register_plugin_ftparser	(	ObPluginParamPtr	param,
		const char *	name,
		ObPluginVersion	version,
		ObPluginFTParser *	ftparser,
		int64_t	ftparser_sizeof,
		const char *	description )

register fulltext parser plugin @NOTE use OBP_REGISTER_FTPARSER instead

参数

param	the param of ObPluginParam which is a passed in param in `plugin::init`
name	fulltext parser name, 64 characters maximum
ftparser	the ftparser struct. The object will be copied.
ftparser_sizeof	the size of `ftparser`
description	the description of the ftparser