rules.ini000644 001751 000000 00000007250 11614564052 013652 0ustar00hightmanwheel000000 000000 ; ; auto regular ; $Id: rules.ini,v 1.7 2011/04/18 09:01:29 hightman Exp $ ; ; special word, 特殊词汇 ; [special] C++ C# R&B P&G J++ J# UTF-8 PS/2 ; ; nostats ; [nostats] about all also an and any are as at be but by both can for from have here if in is it no not of on or our out that the this to up us ; ; 词性语法规则表 ; [attrs] ; c 是连词 n + f(1) = 300 n + m(1) = 500 n(1) + v = 100 n + v(1) = 10 r + n(1) = 1000 r(1) + n = 100 d(1) + r = 100 d(1) + v = 100 v(1) + r = 100 n + m(1) = 500 v + f(1) = 30 v(1) + m = 100 v(1) + n = 5 a + u(1) = 5 v + n(1) = 5 u(1) + a = 2 c(1) + * = 50 * + c(1) = 50 ; ; 名字停用词表 ; [noname] :line = no 给的说对在和是被最所那这有将 就你会与他为不没很了啊哦呵把去 ; ; 双字节符号 ; [symbol] :type = none :line = no `-=[]、‘;/。,|?》《:“{}+—)(*…%¥#·!~ ’”〕〈〉「」『』〖〗【】<> ; ; 姓和外文名共同部分 ; [pubname] :type = prefix :line = no :exclude = noname,symbol,alpha,chnum2 :znum = 1,2 :tf = 5.0 :idf = 3.5 :attr = nr 艾安贝卜戴费福盖戈古赫华霍吉贾金柯赖劳雷黎利林卢 鲁伦罗洛马麦米莫穆齐乔冉萨沙史斯温谢尤詹诸 [pubname2] :type = prefix :line = no :exclude = noname,symbol,alpha,chnum2 :tf = 5.0 :idf = 3.5 :attr = nr 伍陆 [pubname3] :type = prefix :line = no :exclude = noname,symbol,alpha,chnum2 :tf = 5.0 :idf = 3.5 :attr = nr 万章 ; ; 单姓 ; [surname] :type = prefix :line = no :exclude = noname,symbol,alpha,chnum2 :tf = 5.0 :idf = 3.5 :attr = nr :znum = 1,2 敖白班包宝保鲍毕边卞柏蔡曹岑柴昌常车陈成程迟池褚 楚储淳崔刀邓狄刁丁董窦杜端段樊范方房斐丰封冯凤伏 傅甘高耿龚宫勾苟辜谷顾官关管桂郭韩杭郝禾何贺衡洪 侯胡花黄稽姬纪季简翦姜江蒋焦晋靳荆居康空孔匡邝况 蓝郎朗乐冷李理厉励连廉练良梁廖凌刘柳隆龙楼娄吕路 骆麻满茅毛梅孟苗缪闵明牟倪聂牛钮农潘庞裴彭皮朴平 蒲溥浦戚祁钱强秦丘邱仇裘屈瞿权饶任荣容阮瑞芮赛单 商邵佘申沈盛石寿舒宋苏孙邰谭谈汤唐陶滕田佟仝屠涂 汪王危韦魏卫蔚闻翁巫邬武吴奚习夏鲜席冼项萧解辛邢 幸熊徐许宣薛荀颜阎言严彦晏燕杨阳姚叶蚁易殷银尹应 英游于於鱼虞俞余禹喻郁尉袁岳云臧曾查翟湛张赵甄郑 钟周朱竺祝庄卓宗邹祖左肖 ; ; 复姓 ; [surname2] :type = prefix :line = yes :exclude = noname,symbol,alpha,chnum2 :tf = 5.0 :idf = 3.5 :attr = nr :znum = 1, 2 东郭 公孙 皇甫 慕容 欧阳 单于 司空 司马 司徒 澹台 诸葛 ; ; 地点名称 ; [areaname] :type = suffix :znum = 2 :exclude = noname,symbol,alpha,chnum2 :tf = 4.5 :idf = 3.0 :attr = ns :line = no 县市镇村乡区 ; ; 双字地点名称 ; [areaname2] :type = suffix :znum = 2 :exclude = noname,symbol,alpha,chnum2 :tf = 4.5 :idf = 3.0 :attr = ns :line = yes 东路 西路 支路 街道 南路 北路 [munit] :type = none :line = no 萬亿零年点分秒回节名个多届次集 [chnum0] :type = prefix :line = no :tf = 2.5 :idf = 1.0 :attr = mt :include = chnum2,chnum3,munit,pubname3 0 [chnum1] :type = prefix :include = chnum0,chnum1,munit,pubname3 :tf = 3.0 :idf = 1.0 :attr = mt :line = no 一二三四五六七八九十百千 [chnum2] :type = prefix :line = no :tf = 3.0 :idf = 1.0 :attr = mt :include = chnum0,chnum2,chnum3,munit,pubname3 123456789 [chnum3] :type = none :line = no . [chnum4] :type = prefix :line = no :tf = 3.0 :idf = 1.0 :attr = mt :include = chnum4,munit,pubname2,pubname3 壹贰叁肆柒捌玖拾佰仟 [chnum5] :type = prefix :line = no :tf = 3.5 :idf = 2.0 :attr = nz :include = chnum1,munit,pubname3,chnum2 第每 [alpha] :type = prefix :line = no :tf = 2.5 :idf = 1.0 :attr = en :include = alpha abcdefghijklmnopqrstuvwxyz ABCDEFGHIJKLMNOPQRSTUVWXYZ' [foregin] :type = prefix :line = no :tf = 4.0 :idf = 3.0 :attr = nr :include = foregin,pubname,pubname2,pubname3 阿克拉加内亚巴尔姆爱兰西伊杰纳布可夫勒特坦芬尼根登都 伯泰胥俄科索沃森奥瓦茨普蒂塞维大莱德冈墨哥弗库澳哈兹 乌奇切诺里基延达塔卡雅来波迈蓬什比摩曼乃休合娜迪凯帕 桑佩蒙博托格泽及希匹印埃努烈累法图喀土腓耶逊宾 rules.utf8.ini000644 001751 000000 00000010544 11614564052 014537 0ustar00hightmanwheel000000 000000 ; ; auto regular(utf-8) ; $Id: rules.utf8.ini,v 1.7 2011/04/18 09:01:29 hightman Exp $ ; ; special word, 鐗规畩璇嶆眹 ; [special] C++ C# R&B P&G J++ J# UTF-8 PS/2 ; ; nostats ; [nostats] about all also an and any are as at be but by both can for from have here if in is it no not of on or our out that the this to up us ; ; 璇嶆ц娉曡鍒欒〃 ; [attrs] ; c 鏄繛璇 n + f(1) = 300 n + m(1) = 500 n(1) + v = 100 n + v(1) = 10 r + n(1) = 1000 r(1) + n = 100 d(1) + r = 100 d(1) + v = 100 v(1) + r = 100 n + m(1) = 500 v + f(1) = 30 v(1) + m = 100 v(1) + n = 3 a + u(1) = 5 v + n(1) = 5 u(1) + a = 2 c(1) + * = 50 * + c(1) = 50 ; ; 鍚嶅瓧鍋滅敤璇嶈〃 ; [noname] :line = no 缁欑殑璇村鍦ㄥ拰鏄鏈鎵閭h繖鏈夊皢 浣犱細涓庝粬涓轰笉娌″緢浜嗗晩鍝﹀懙鎶婂幓 ; ; 鍙屽瓧鑺傜鍙 ; [symbol] :type = none :line = no 锝锛嶏紳锛伙冀銆佲橈紱锛忋傦紝锝滐紵銆嬨婏細鈥滐經锝濓紜鈥旓級锛堬紛鈥︼紖锟ワ純路锛侊綖 鈥欌濄曘堛夈屻嶃庛忋栥椼愩戯紲锛 ; ; 濮撳拰澶栨枃鍚嶅叡鍚岄儴鍒 ; [pubname] :type = prefix :line = no :exclude = noname,symbol,alpha,chnum2 :znum = 1,2 :tf = 5.0 :idf = 3.5 :attr = nr 鑹惧畨璐濆崪鎴磋垂绂忕洊鎴堝彜璧崕闇嶅悏璐鹃噾鏌禆鍔抽浄榛庡埄鏋楀崲 椴佷鸡缃楁礇椹害绫宠帿绌嗛綈涔斿唹钀ㄦ矙鍙叉柉娓╄阿灏よ┕璇 [pubname2] :type = prefix :line = no :exclude = noname,symbol,alpha,chnum2 :tf = 5.0 :idf = 3.5 :attr = nr 浼嶉檰 [pubname3] :type = prefix :line = no :exclude = noname,symbol,alpha,chnum2 :tf = 5.0 :idf = 3.5 :attr = nr 涓囩珷 ; ; 鍗曞 ; [surname] :type = prefix :line = no :exclude = noname,symbol,alpha,chnum2 :tf = 5.0 :idf = 3.5 :attr = nr :znum = 1,2 鏁栫櫧鐝寘瀹濅繚椴嶆瘯杈瑰崬鏌忚敗鏇瑰矐鏌存槍甯歌溅闄堟垚绋嬭繜姹犺 妤氬偍娣冲磾鍒閭撶媱鍒佷竵钁g鏉滅娈垫▕鑼冩柟鎴挎枑涓板皝鍐嚖浼 鍌呯敇楂樿块練瀹嬀鑻熻緶璋烽【瀹樺叧绠℃閮煩鏉儩绂句綍璐鸿 娲 渚儭鑺遍粍绋藉К绾绠缈﹀姹熻拫鐒︽檵闈宠崋灞呭悍绌哄瓟鍖¢倽鍐 钃濋儙鏈椾箰鍐锋潕鐞嗗帀鍔辫繛寤夌粌鑹寤栧噷鍒樻煶闅嗛緳妤煎▌鍚曡矾 楠嗛夯婊¤寘姣涙瀛熻嫍缂椀鏄庣墴鍊亗鐗涢挳鍐滄綐搴炶4褰毊鏈村钩 钂叉亥娴︽垰绁侀挶寮虹Е涓橀偙浠囪灞堢灴鏉冮ザ浠昏崳瀹归槷鐟炶姰璧涘崟 鍟嗛偟浣樼敵娌堢洓鐭冲鑸掑畫鑻忓瓩閭拌碍璋堟堡鍞愰櫠婊曠敯浣熶粷灞犳秱 姹帇鍗遍煢榄忓崼钄氶椈缈佸帆閭鍚村涔犲椴滃腑鍐奸」钀цВ杈涢偄 骞哥唺寰愯瀹h枦鑽棰滈槑瑷涓ュ溅鏅忕嚂鏉ㄩ槼濮氬彾铓佹槗娈烽摱灏瑰簲 鑻辨父浜庢柤楸艰櫈淇炰綑绂瑰柣閮佸皦琚佸渤浜戣嚙鏇炬煡缈熸箾寮犺档鐢勯儜 閽熷懆鏈辩绁濆簞鍗撳畻閭圭宸﹁倴 ; ; 澶嶅 ; [surname2] :type = prefix :line = yes :exclude = noname,symbol,alpha,chnum2 :tf = 5.0 :idf = 3.5 :attr = nr :znum = 1, 2 涓滈儹 鍏瓩 鐨囩敨 鎱曞 娆ч槼 鍗曚簬 鍙哥┖ 鍙搁┈ 鍙稿緬 婢瑰彴 璇歌憶 ; ; 鍦扮偣鍚嶇О ; [areaname] :type = suffix :znum = 2 :exclude = noname,symbol,alpha,chnum2 :tf = 4.5 :idf = 3.0 :attr = ns :line = no 鍘垮競闀囨潙涔″尯 ; ; 鍙屽瓧鍦扮偣鍚嶇О ; [areaname2] :type = suffix :znum = 2 :exclude = noname,symbol,alpha,chnum2 :tf = 4.5 :idf = 3.0 :attr = ns :line = yes 涓滆矾 瑗胯矾 鏀矾 琛楅亾 鍗楄矾 鍖楄矾 [munit] :type = none :line = no 钀嚎闆跺勾鐐瑰垎绉掑洖鑺傚悕涓灞婃闆 [chnum0] :type = prefix :line = no :tf = 2.5 :idf = 1.0 :attr = mt :include = chnum2,chnum3,munit,pubname3 锛 [chnum1] :type = prefix :include = chnum0,chnum1,munit,pubname3 :tf = 3.0 :idf = 1.0 :attr = mt :line = no 涓浜屼笁鍥涗簲鍏竷鍏節鍗佺櫨鍗 [chnum2] :type = prefix :line = no :tf = 3.0 :idf = 1.0 :attr = mt :include = chnum0,chnum2,chnum3,munit,pubname3 锛戯紥锛擄紨锛曪紪锛楋紭锛 [chnum3] :type = none :line = no 锛 [chnum4] :type = prefix :line = no :tf = 3.0 :idf = 1.0 :attr = mt :include = chnum4,munit,pubname2,pubname3 澹硅窗鍙佽倖鏌掓崒鐜栨嬀浣颁粺 [chnum5] :type = prefix :line = no :tf = 3.5 :idf = 2.0 :attr = nz :include = chnum1,munit,pubname3,chnum2 绗瘡 [alpha] :type = prefix :line = no :tf = 2.5 :idf = 1.0 :attr = en :include = alpha 锝侊絺锝冿絼锝咃絾锝囷綀锝夛綂锝嬶綄锝嶏綆锝忥綈锝戯綊锝擄綌锝曪綎锝楋綐锝欙綒 锛★饥锛o激锛ワ鸡锛э绩锛╋吉锛棘锛籍锛及锛憋疾锛筹即锛碉级锛凤几锛癸己锛 [foregin] :type = prefix :line = no :tf = 4.0 :idf = 3.0 :attr = nr :include = foregin,pubname,pubname2,pubname3 闃垮厠鎷夊姞鍐呬簹宸村皵濮嗙埍鍏拌タ浼婃澃绾冲竷鍙か鍕掔壒鍧﹁姮灏兼牴鐧婚兘 浼嘲鑳ヤ縿绉戠储娌冩.濂ョ摝鑼ㄦ櫘钂傚缁村ぇ鑾卞痉鍐堝ⅷ鍝ュ紬搴撴境鍝堝吂 涔屽鍒囪閲屽熀寤惰揪濉斿崱闆呮潵娉㈣繄钃粈姣旀懇鏇间箖浼戝悎濞滆开鍑笗 妗戜僵钂欏崥鎵樻牸娉藉強甯屽尮鍗板焹鍔儓绱硶鍥惧杸鍦熻厯鑰堕婂 rules_cht.utf8.ini000644 001751 000000 00000010533 11614564052 015373 0ustar00hightmanwheel000000 000000 ; ; auto regular(utf-8) ; $Id: rules_cht.utf8.ini,v 1.6 2010/05/23 10:01:00 hightman Exp $ ; ; special word, 鐗规畩瑭炲尟 ; [special] C++ C# R&B P&G J++ J# UTF-8 PS/2 ; ; nostats ; [nostats] about all also an and any are as at be but by both can for from have here if in is it no not of on or our out that the this to up us ; ; 璇嶆ц娉曡鍒欒〃 ; [attrs] ; c 鏄繛璇 n + f(1) = 300 n + m(1) = 500 n(1) + v = 100 n + v(1) = 10 r + n(1) = 1000 r(1) + n = 100 d(1) + r = 100 d(1) + v = 100 v(1) + r = 100 n + m(1) = 500 v + f(1) = 30 v(1) + m = 100 v(1) + n = 5 a + u(1) = 5 v + n(1) = 5 c(1) + * = 50 * + c(1) = 50 ; ; 鍚嶅瓧鍋滅敤瑭炶〃 ; [noname] :line = no 绲︾殑瑾皪鍦ㄥ拰鏄鏈鎵閭i欐湁灏 浣犳渻鑸囦粬鐐轰笉娌掑緢浜嗗晩鍝﹀懙鎶婂幓 ; ; 闆欏瓧绡绗﹁櫉 ; [symbol] :type = none :line = no 锝锛嶏紳锛伙冀銆佲橈紱锛忋傦紝锝滐紵銆嬨婏細鈥滐經锝濓紜鈥旓級锛堬紛鈥︼紖锟ワ純路锛侊綖 鈥欌濄曘堛夈屻嶃庛忋栥椼愩戯紲锛 ; ; 濮撳拰澶栨枃鍚嶅叡鍚岄儴鍒 ; [pubname] :type = prefix :line = no :exclude = noname,symbol,alpha,chnum2 :znum = 1,2 :tf = 5.0 :idf = 3.5 :attr = nr 鑹惧畨璨濆崪鎴磋不绂忚搵鎴堝彜璧彲闇嶅悏璩堥噾鏌炒鍕為浄榛庡埄鏋楃洤 榄緟娲涢Μ楹ョ背鑾﹩榻婂柆鍐夎柀娌欏彶鏂韩璎濆挨瑭硅 [pubname2] :type = prefix :line = no :exclude = noname,symbol,alpha,chnum2 :tf = 5.0 :idf = 3.5 :attr = nr 浼嶉櫢 [pubname3] :type = prefix :line = no :exclude = noname,symbol,alpha,chnum2 :tf = 5.0 :idf = 3.5 :attr = nr 钀珷 ; ; 鍠 ; [surname] :type = prefix :line = no :exclude = noname,symbol,alpha,chnum2 :tf = 5.0 :idf = 3.5 :attr = nr :znum = 1,2 鏁栫櫧鐝寘瀵朵繚楫戠暍閭婂崬鏌忚敗鏇瑰矐鏌存槍甯歌粖闄虫垚绋嬮伈姹犺 妤氬劜娣冲磾鍒閯х媱鍒佷竵钁g珖鏉滅娈垫▕鑼冩柟鎴挎枑璞愬皝棣吵浼 鍌呯敇楂樿块緮瀹嬀鑻熻緶璋烽¨瀹橀棞绠℃閮煋鏉儩绂句綍璩琛℃椽 渚儭鑺遍粌绋藉К绱瀛g啊缈﹀姹熻敚鐒︽檳闈宠崐灞呭悍绌哄瓟鍖¢労娉 钘嶉儙鏈楁▊鍐锋潕鐞嗗幉鍕甸e粔绶磋壇妯戝粬鍑屽妷鏌抽殕榫嶆〒濠佸憘璺 椐遍夯婊胯寘姣涙瀛熻嫍绻嗛枖鏄庣墴鍊伓鐗涢垥杈叉綐榫愯4褰毊妯稿钩 钂叉亥娴︽垰绁侀將寮风Е涓橀偙浠囪灞堢灴娆婇浠绘Ξ瀹归槷鐟炶姰璩藉柈 鍟嗛偟浣樼敵娌堢洓鐭冲=鑸掑畫铇囧閭拌瓪璜囨汞鍞愰櫠婊曠敯浣熶粷灞犲 姹帇鍗遍煁榄忚钄氳仦缈佸帆閯旀鍚冲缈掑楫腑鍐奸爡钑В杈涢偄 骞哥唺寰愯ū瀹h枦鑽椤忛柣瑷鍤村渐鏅忕嚂妤婇櫧濮氳憠锜绘槗娈烽妧灏规噳 鑻遍亰鏂兼柤榄氳櫈淇炰綑绂瑰柣楝卞皦琚佸渤闆茶嚙鏇炬煡缈熸箾寮佃稒鐢勯劖 閻樺懆鏈辩绁濊帄鍗撳畻閯掔宸﹁倴 ; ; 寰╁ ; [surname2] :type = prefix :line = yes :exclude = noname,symbol,alpha,chnum2 :tf = 5.0 :idf = 3.5 :attr = nr :znum = 1, 2 鏉遍儹 鍏 鐨囩敨 鎱曞 姝愰櫧 鍠柤 鍙哥┖ 鍙搁Μ 鍙稿緬 婢瑰彴 璜歌憶 ; ; 鍦伴粸鍚嶇ū ; [areaname] :type = suffix :znum = 2 :exclude = noname,symbol,alpha,chnum2 :tf = 4.5 :idf = 3.0 :attr = ns :line = no 绺e競閹潙閯夊崁 ; ; 闆欏瓧鍦伴粸鍚嶇ū ; [areaname2] :type = suffix :znum = 2 :exclude = noname,symbol,alpha,chnum2 :tf = 4.5 :idf = 3.0 :attr = ns :line = yes 鏉辫矾 瑗胯矾 鏀矾 琛楅亾 鍗楄矾 鍖楄矾 [munit] :type = none :line = no 钀剟闆跺勾榛炲垎绉掑洖绡鍚嶅嬪灞嗘闆 [chnum0] :type = prefix :line = no :tf = 2.5 :idf = 1.0 :attr = mt :include = chnum2,chnum3,munit,pubname3 锛 [chnum1] :type = prefix :include = chnum0,chnum1,munit,pubname3 :tf = 3.0 :idf = 1.0 :attr = mt :line = no 涓浜屼笁鍥涗簲鍏竷鍏節鍗佺櫨鍗 [chnum2] :type = prefix :line = no :tf = 3.0 :idf = 1.0 :attr = mt :include = chnum0,chnum2,chnum3,munit,pubname3 锛戯紥锛擄紨锛曪紪锛楋紭锛 [chnum3] :type = none :line = no 锛 [chnum4] :type = prefix :line = no :tf = 3.0 :idf = 1.0 :attr = mt :include = chnum4,munit,pubname2,pubname3 澹硅渤涓夎倖鏌掓崒鐜栨嬀浣颁粺 [chnum5] :type = prefix :line = no :tf = 3.5 :idf = 2.0 :attr = nz :include = chnum1,munit,pubname3,chnum2 绗瘡 [alpha] :type = prefix :line = no :tf = 2.5 :idf = 1.0 :attr = en :include = alpha 锝侊絺锝冿絼锝咃絾锝囷綀锝夛綂锝嬶綄锝嶏綆锝忥綈锝戯綊锝擄綌锝曪綎锝楋綐锝欙綒 锛★饥锛o激锛ワ鸡锛э绩锛╋吉锛棘锛籍锛及锛憋疾锛筹即锛碉级锛凤几锛癸己锛 [foregin] :type = prefix :line = no :tf = 4.0 :idf = 3.0 :attr = nr :include = foregin,pubname,pubname2,pubname3 闃垮厠鎷夊姞鍏т簽宸寸埦濮嗘剾铇タ浼婂倯绱嶅竷鍙か鍕掔壒鍧﹁姮灏兼牴鐧婚兘 浼嘲鑳ヤ縿绉戠储娌冩.濂х摝鑼ㄦ櫘钂傚缍ぇ钀婂痉宀″ⅷ鍝ュ紬搴境鍝堣尣 鐑忓鍒囪瑁″熀寤堕仈濉斿崱闆呬締娉㈤倎钃粈姣旀懇鏇间箖浼戝悎濞滆开鍑卞笗 妗戜僵钂欏崥鎵樻牸婢ゅ強甯屽尮鍗板焹鍔儓绱硶鍦栧杸鍦熻厯鑰堕仠璩