lionsoul2014/friso

Initialized in 0.088911sec
Mode: Complex
+-Version: 1.6.2 (UTF-8)
+---------------------------------------------------------------+
| Friso - a Chinese word segmentation writen by c.              |
| bug report email - [email protected].                   |
| or: visit https://github.com/lionsoul2014/friso.              |
|     java edition for https://github.com/lionsoul2014/jcseg    |
| type 'quit' to exit the program.                              |
+---------------------------------------------------------------+
friso>> 

歧义和同义词:研究生命起源，混合词: 做B超检查身体，x射线本质是什么，今天去奇都ktv唱卡拉ok去，哆啦a梦是一个动漫中的主角，单位和全角: 2009年８月６日开始大学之旅，岳阳今天的气温为38.6℃, 也就是101.48℉, 英文数字: bug report [email protected] or visit http://code.google.com/p/jcseg, we all admire the hacker spirit!特殊数字: ① ⑩ ⑽ ㈩.

歧义 和 同义词 : 研究 琢磨 研讨 钻研 生命 起源 ， 混合词 : 做 b超 检查 身体 ， x射线 本质 是 什么 ， 今天 去 奇都ktv 唱 卡拉ok 去 ， 哆啦a梦 是 一个 动漫 中 的 主角 ， 单位 和 全角 : 2009年 8月 6日 开始 大学 之旅 ， 岳阳 今天 的 气温 为 38.6℃ , 也就是 101.48℉ , 英文 英语 数字 : bug report example gmail com [email protected] or visit http : / / code google com code.google.com / p / jcseg , we all admire appreciate like love enjoy the hacker spirit mind ! 特殊 数字 : .

make
sudo make install

# for testing
make testing

make

# friso configuration file.
#	do not change the name of the left key.
# @email	[email protected]
# @date		2012-12-20
#

# charset, only UTF8 and GBK support.
# set it with UTF8(0) or GBK(1)
friso.charset = 0

# lexicon directory absolute path.
#	the value must end with '/'
# this will tell friso how to find friso.lex.ini configuration file and all the lexicon files.
#
# if it is not start with '/' for linux, or matches no ':' for winnt in its value 
#	friso will search the friso.lex.ini relative to friso.ini
# absolute path search:
# linux:	friso.lex_dir = /c/products/friso/dict/UTF-8/
# Winnt:	friso.lex_dir = D:/products/friso/dict/UTF-8/
# relative path search (All system)
friso.lex_dir = ./vendors/dict/UTF-8/

# the maximum matching length.
friso.max_len = 5 

# 1 for recognition chinese name.
#	and 0 for closed it.
friso.r_name = 1

# the maximum length for the cjk words in a
#	chinese and english mixed word.
friso.mix_len = 2

# the maxinum length for the chinese last name adron.
friso.lna_len = 1

# append the synonyms words
friso.add_syn = 1

# clear the stopwords or not (1 to open it and 0 to close it)
# @date 2013-06-13
friso.clr_stw = 0

# keep the unrecongized words or not (1 to open it and 0 to close it)
# @date 2013-06-13
friso.keep_urec = 0

# use sphinx output style like 'admire|love|enjoy einsten'
# @date 2013-10-25
friso.spx_out = 0

# start the secondary segmentation for complex english token.
friso.en_sseg = 1

# min length of the secondary segmentation token. (better larger than 1)
friso.st_minl = 2

# default keep punctuations for english token.
friso.kpuncs = @%.#&+

# the threshold value for a char not a part of a chinese name.
friso.nthreshold = 2000000

# default mode for friso.
# 1 : simple mode - simply maxmum matching algorithm.
# 2 : complex mode - four rules of mmseg alogrithm.
# 3 : detect mode - only return the words that the do exists in the lexicon
friso.mode = 2

/* 第一步：申明三个对象 */
friso_t friso;          /* Friso 分词对象 */
friso_config_t config;  /* Friso 配置对象 */
friso_task_t task;      /* Friso 任务对象 */

/* 第二步：初始化相应的对象 */
friso  = friso_new();
config = friso_new_config();
task   = friso_new_task();

/* 从friso.ini配置文件中初始化 friso */
if (friso_init_from_ifile(friso, config, "friso.ini文件地址") != 1) {
    /* friso 初始化失败 */
}

/*
 * 切分模式默认来自friso.ini中的设置
 * 可以通过friso_set_mode函数自定义切分模式(简易，复杂，检测模式)
 * 简易模式：__FRISO_SIMPLE_MODE__
 * 复杂模式：__FRISO_COMPLEX_MODE__
 * 检测模式：__FRISO_DETECT_MODE__
 * 例如，这里设置为使用复杂模式分词：
*/
friso_set_mode(config, __FRISO_COMPLEX_MODE__);


/* 第三步：设置分词内容 */
friso_set_text(task, "分词的文本");

/* 第四步：获取分词内容 */
while (config->next_token(friso, config, task) != NULL) {
    /* 
      task存储了分词的结果，
      task->token->word: 词条内容
      task->token->offset: 词条在原始文本的offset
      task->token->length: 词条的长度(字节数)
      task->token->rlen: 词条的真正字节数(Friso转换后的长度-字节数)
    */
    printf("%s ", task->token->word);
}


/* 第五步：释放对象 */
friso_free_task(task);
friso_free_config(config);
friso_free(friso);

typedef enum {
 __LEX_CJK_WORDS__ = 0,     // 普通 CJK 词库
 __LEX_CJK_UNITS__ = 1,     // CJK 单位词库
 __LEX_ECM_WORDS__ = 2,     // 英中混合词(例如: b 超)
 __LEX_CEM_WORDS__ = 3,     // 中英混合词(例如: 卡拉 ok).
 __LEX_CN_LNAME__  = 4,     // 中文姓氏
 __LEX_CN_SNAME__  = 5,     // 中文单姓名词库
 __LEX_CN_DNAME1__ = 6,     // 中文双姓名首字词库
 __LEX_CN_DNAME2__ = 7,     // 中文双姓名尾字词库
 __LEX_CN_LNA__ = 8,        // 中文姓氏修饰词词库
 __LEX_STOPWORDS__ = 9,     // 停止词词库
 __LEX_ENPUN_WORDS__ = 10,  // 英文和标点混合词库(例如: c++)
 __LEX_OTHER_WORDS__ = 15,  // 无用
 __LEX_NCSYN_WORDS__ = 16   // 无用
} friso_lex_t;

# main lexion
__LEX_CJK_WORDS__ :[
    lex-main.lex;
    lex-admin.lex;
    lex-chars.lex;
    lex-cn-mz.lex;
    lex-cn-place.lex;
    lex-company.lex;
    lex-festival.lex;
    lex-flname.lex;
    lex-food.lex;
    lex-lang.lex;
    lex-nation.lex;
    lex-net.lex;
    lex-org.lex;
    lex-touris.lex;
# add more here
]
# single chinese unit lexicon
__LEX_CJK_UNITS__ :[
    lex-units.lex;
]
# chinese and english mixed word lexicon like "b超".
__LEX_ECM_WORDS__:[
    lex-ecmixed.lex;
]
# english and chinese mixed word lexicon like "卡拉ok".
__LEX_CEM_WORDS__:[
    lex-cemixed.lex;
]
# chinese last name lexicon.
__LEX_CN_LNAME__:[
    lex-lname.lex;
]
# single name words lexicon.
__LEX_CN_SNAME__:[
    lex-sname.lex;
]
# first word of a double chinese name.
__LEX_CN_DNAME1__:[
    lex-dname-1.lex;
]
# second word of a double chinese name.
__LEX_CN_DNAME2__:[
    lex-dname-2.lex;
]
# chinese last name decorate word.
__LEX_CN_LNA__:[
    lex-ln-adorn.lex;
]
# stopwords lexicon
__LEX_STOPWORDS__:[
    lex-stopword.lex;
]
# english and punctuation mixed words lexicon.
__LEX_ENPUN_WORDS__:[
    lex-en-pun.lex;
]
# english words(for synonyms words)
__LEX_EN_WORDS__:[
    lex-en.lex;
]

# main lexion
__LEX_CJK_WORDS__ :[
    lex-main.lex;
    lex-admin.lex;
    lex-chars.lex;
    lex-cn-mz.lex;
    lex-cn-place.lex;
    lex-company.lex;
    lex-festival.lex;
    lex-flname.lex;
    lex-food.lex;
    lex-lang.lex;
    lex-nation.lex;
    lex-net.lex;
    lex-org.lex;
    lex-touris.lex;
# 新增的植物名称词库
    lex-plants.lex;
# add more here
]

词条/同义词集合

你好/null
研究/琢磨,研讨,钻研