Updated the Simplified to Traditional table; Added comments crediting sources used...
authorZheng Zhu <zhengzhu@users.mediawiki.org>
Sun, 19 Sep 2004 01:30:37 +0000 (01:30 +0000)
committerZheng Zhu <zhengzhu@users.mediawiki.org>
Sun, 19 Sep 2004 01:30:37 +0000 (01:30 +0000)
includes/ZhConversion.php

index ae239d2..6fca80f 100644 (file)
@@ -1,5 +1,21 @@
 <?php
-/* Simplified/Traditional conversion tables */
+/* Simplified/Traditional Chinese conversion tables
+
+   The character-to-character mappings are mainly extracted from the
+   Unihan database from the 4.0.1 version of the Unicode standard,
+   with some modification adapted from the following paper published
+   in China:
+   冯寿忠,“非对称繁简字”对照表, 《语文建设通讯》1997-9第53期.
+   The paper is available from
+   /http://www.yywzw.com/jt/feng/fengb01.htm
+
+   The phrases are extracted from various phrase tables in the SCIM
+   package (http://www.freedesktop.org/Software/scim), and the mappings
+   of the phrases are computed using the character-to-character
+   mappings. Only phrases that contains one-to-many
+   character-to-character mappings are included, and the length of the
+   phrases are limited to below 5 characters.
+*/
 
 $wgZhSimp2Trad=array(
 "万"=>"萬",
@@ -2645,7 +2661,6 @@ $wgZhSimp2Trad=array(
 "硷度" =>    "鹼度",
 "硷性" =>    "鹼性",
 "硷液" =>    "鹼液",
-"古柯硷" =>         "古柯鹼",
 "什么" =>    "什麼",
 "多么" =>    "多麼",
 "干么" =>    "幹麼",
@@ -5013,410 +5028,6 @@ $wgZhSimp2Trad=array(
 "庞克" =>    "龐克",
 "龟壳" =>    "龜殼",
 "当" =>    "當",
-"一夥人" =>         "一夥人",
-"一夥儿" =>         "一夥兒",
-"一年里" =>         "一年裡",
-"一条线" =>         "一條線",
-"一院制" =>         "一院制",
-"七巧板" =>         "七巧板",
-"七里香" =>         "七里香",
-"三八制" =>         "三八制",
-"三折肱" =>         "三折肱",
-"三极管" =>         "三極管",
-"三角板" =>         "三角板",
-"三只手" =>         "三隻手",
-"中文系" =>         "中文系",
-"中台路" =>         "中臺路",
-"丹斯里" =>         "丹斯里",
-"主播台" =>         "主播台",
-"主机板" =>         "主機板",
-"二部制" =>         "二部制",
-"五台山" =>         "五台山",
-"五斗米" =>         "五斗米",
-"五线谱" =>         "五線譜",
-"五里雾" =>         "五里霧",
-"亚松森" =>         "亞松森",
-"交管系" =>         "交管系",
-"人类系" =>         "人類系",
-"介系词" =>         "介系詞",
-"代议制" =>         "代議制",
-"企管系" =>         "企管系",
-"伊拉克" =>         "伊拉克",
-"伯克来" =>         "伯克來",
-"来福线" =>         "來福線",
-"供应线" =>         "供應線",
-"保险系" =>         "保險系",
-"信号台" =>         "信號台",
-"内阁制" =>         "內閣制",
-"两院制" =>         "兩院制",
-"八字胡" =>         "八字鬍",
-"八斗子" =>         "八斗子",
-"公有制" =>         "公有制",
-"公训系" =>         "公訓系",
-"准考证" =>         "准考證",
-"分封制" =>         "分封制",
-"分水线" =>         "分水線",
-"分页线" =>         "分頁線",
-"划不来" =>         "划不來",
-"划得来" =>         "划得來",
-"刮地皮" =>         "刮地皮",
-"刮胡刀" =>         "刮鬍刀",
-"制海权" =>         "制海權",
-"制空权" =>         "制空權",
-"制高点" =>         "制高點",
-"加旁线" =>         "加旁線",
-"动物系" =>         "動物系",
-"劳工系" =>         "勞工系",
-"化妆台" =>         "化妝台",
-"化学奖" =>         "化學獎",
-"千百只" =>         "千百隻",
-"南台路" =>         "南臺路",
-"卡洛里" =>         "卡洛里",
-"卡路里" =>         "卡路里",
-"印刷系" =>         "印刷系",
-"古柯硷" =>         "古柯鹼",
-"可怜虫" =>         "可憐虫",
-"台机路" =>         "台機路",
-"司令台" =>         "司令台",
-"司令台" =>         "司令臺",
-"合得来" =>         "合得來",
-"合桃街" =>         "合桃街",
-"合浦街" =>         "合浦街",
-"合经系" =>         "合經系",
-"合订本" =>         "合訂本",
-"後北街" =>         "后北街",
-"後安路" =>         "后安路",
-"後平路" =>         "后平路",
-"向心力" =>         "向心力",
-"告示板" =>         "告示板",
-"和平奖" =>         "和平獎",
-"咸认为" =>         "咸認為",
-"商数系" =>         "商數系",
-"启德道" =>         "啟德道",
-"启昌街" =>         "啟昌街",
-"启超道" =>         "啟超道",
-"嘉咸街" =>         "嘉咸街",
-"回归线" =>         "回歸線",
-"国文系" =>         "國文系",
-"国贸系" =>         "國貿系",
-"园艺系" =>         "園藝系",
-"土壤系" =>         "土壤系",
-"土木系" =>         "土木系",
-"地平线" =>         "地平線",
-"地政系" =>         "地政系",
-"地理系" =>         "地理系",
-"地质系" =>         "地質系",
-"埃荣冲" =>         "埃榮衝",
-"塑胶板" =>         "塑膠板",
-"塔里木" =>         "塔里木",
-"压克力" =>         "壓克力",
-"外交系" =>         "外交系",
-"外文系" =>         "外文系",
-"夜光表" =>         "夜光錶",
-"大传系" =>         "大傳系",
-"天文台" =>         "天文台",
-"天文台" =>         "天文臺",
-"天花板" =>         "天花板",
-"太阳系" =>         "太陽系",
-"太麻里" =>         "太麻里",
-"奥克兰" =>         "奧克蘭",
-"委员制" =>         "委員制",
-"姜太公" =>         "姜太公",
-"姜子牙" =>         "姜子牙",
-"子午线" =>         "子午線",
-"孟姜女" =>         "孟姜女",
-"学区制" =>         "學區制",
-"宇宙线" =>         "宇宙線",
-"安眠药" =>         "安眠藥",
-"家政系" =>         "家政系",
-"家长制" =>         "家長制",
-"密苏里" =>         "密蘇里",
-"富台街" =>         "富臺街",
-"富里乡" =>         "富里鄉",
-"封锁线" =>         "封鎖線",
-"对角线" =>         "對角線",
-"小夥子" =>         "小夥子",
-"小班制" =>         "小班制",
-"尼克森" =>         "尼克森",
-"尼龙线" =>         "尼龍線",
-"屯田制" =>         "屯田制",
-"工教系" =>         "工教系",
-"工业系" =>         "工業系",
-"工管系" =>         "工管系",
-"工设系" =>         "工設系",
-"巧克力" =>         "巧克力",
-"巴拉松" =>         "巴拉松",
-"巴洛克" =>         "巴洛克",
-"巴尔干" =>         "巴爾幹",
-"巴里岛" =>         "巴里島",
-"市政系" =>         "市政系",
-"师铎奖" =>         "師鐸獎",
-"干德道" =>         "干德道",
-"平行线" =>         "平行線",
-"干下去" =>         "幹下去",
-"干不了" =>         "幹不了",
-"干不成" =>         "幹不成",
-"干起来" =>         "幹起來",
-"康百克" =>         "康百克",
-"广告系" =>         "廣告系",
-"广电系" =>         "廣電系",
-"延长线" =>         "延長線",
-"建筑系" =>         "建築系",
-"弹珠台" =>         "彈珠檯",
-"徐光启" =>         "徐光啟",
-"御花园" =>         "御花園",
-"复健系" =>         "復健系",
-"德文系" =>         "德文系",
-"心理系" =>         "心理系",
-"忘忧谷" =>         "忘憂谷",
-"情报台" =>         "情報台",
-"应化系" =>         "應化系",
-"应数系" =>         "應數系",
-"戏剧系" =>         "戲劇系",
-"所有制" =>         "所有制",
-"手术台" =>         "手術台",
-"打印台" =>         "打印台",
-"打擂台" =>         "打擂臺",
-"扣板机" =>         "扣板機",
-"抛物线" =>         "拋物線",
-"指挥台" =>         "指揮台",
-"捋虎须" =>         "捋虎鬚",
-"采石场" =>         "採石場",
-"采石厂" =>         "採石廠",
-"揭示板" =>         "揭示板",
-"搭错线" =>         "搭錯線",
-"政治系" =>         "政治系",
-"教心系" =>         "教心系",
-"教育系" =>         "教育系",
-"文学奖" =>         "文學獎",
-"斑马线" =>         "斑馬線",
-"新闻系" =>         "新聞系",
-"断头台" =>         "斷頭台",
-"日文系" =>         "日文系",
-"昆虫系" =>         "昆蟲系",
-"景观系" =>         "景觀系",
-"智慧板" =>         "智慧板",
-"会员制" =>         "會員制",
-"会计系" =>         "會計系",
-"服务台" =>         "服務台",
-"本松路" =>         "本松路",
-"材料系" =>         "材料系",
-"松南路" =>         "松南路",
-"松寿路" =>         "松壽路",
-"松安路" =>         "松安路",
-"松德路" =>         "松德路",
-"松文路" =>         "松文路",
-"松智路" =>         "松智路",
-"松节油" =>         "松節油",
-"松兴路" =>         "松興路",
-"松隆路" =>         "松隆路",
-"板着脸" =>         "板著臉",
-"板金科" =>         "板金科",
-"板门店" =>         "板門店",
-"柏克莱" =>         "柏克萊",
-"查号台" =>         "查號台",
-"核工系" =>         "核工系",
-"梁启超" =>         "梁啟超",
-"梳妆台" =>         "梳妝台",
-"森林系" =>         "森林系",
-"植物系" =>         "植物系",
-"植病系" =>         "植病系",
-"标准制" =>         "標準制",
-"机械系" =>         "機械系",
-"止痛药" =>         "止痛藥",
-"杀虫药" =>         "殺虫藥",
-"杀虫药" =>         "殺蟲藥",
-"气象台" =>         "氣象台",
-"气象系" =>         "氣象系",
-"水利系" =>         "水利系",
-"水平线" =>         "水平線",
-"沈剑虹" =>         "沈劍虹",
-"沈甸甸" =>         "沈甸甸",
-"法律系" =>         "法律系",
-"法文系" =>         "法文系",
-"法兰克" =>         "法蘭克",
-"洛克道" =>         "洛克道",
-"流水线" =>         "流水線",
-"流理台" =>         "流理台",
-"流线型" =>         "流線型",
-"海岸线" =>         "海岸線",
-"海平线" =>         "海平線",
-"海洋系" =>         "海洋系",
-"减肥药" =>         "減肥藥",
-"测量系" =>         "測量系",
-"渔业系" =>         "漁業系",
-"漆咸道" =>         "漆咸道",
-"乌克兰" =>         "烏克蘭",
-"乌干达" =>         "烏干達",
-"营养系" =>         "營養系",
-"父权制" =>         "父權制",
-"牙医系" =>         "牙醫系",
-"牛肉面" =>         "牛肉麵",
-"物理奖" =>         "物理獎",
-"物理系" =>         "物理系",
-"特别奖" =>         "特別獎",
-"特效药" =>         "特效藥",
-"奖学金" =>         "獎學金",
-"兽医系" =>         "獸醫系",
-"玻璃板" =>         "玻璃板",
-"环境系" =>         "環境系",
-"瓜子壳" =>         "瓜子殼",
-"甘谷街" =>         "甘谷街",
-"生命线" =>         "生命線",
-"生物系" =>         "生物系",
-"生产线" =>         "生產線",
-"产品线" =>         "產品線",
-"畜牧系" =>         "畜牧系",
-"当不起" =>         "當不起",
-"发射台" =>         "發射台",
-"百分制" =>         "百分制",
-"尽人事" =>         "盡人事",
-"尽全力" =>         "盡全力",
-"尽可能" =>         "盡可能",
-"尽本分" =>         "盡本分",
-"尽义务" =>         "盡義務",
-"石钟乳" =>         "石鐘乳",
-"破折号" =>         "破折號",
-"磁力线" =>         "磁力線",
-"社工系" =>         "社工系",
-"社教系" =>         "社教系",
-"社会系" =>         "社會系",
-"祝英台" =>         "祝英台",
-"私有制" =>         "私有制",
-"窝里反" =>         "窩裡反",
-"第一线" =>         "第一線",
-"第二线" =>         "第二線",
-"精工舍" =>         "精工舍",
-"系主任" =>         "系主任",
-"纪念奖" =>         "紀念獎",
-"纺织系" =>         "紡織系",
-"统计系" =>         "統計系",
-"经合会" =>         "經合會",
-"经济奖" =>         "經濟獎",
-"经济系" =>         "經濟系",
-"纵贯线" =>         "縱貫線",
-"绷着脸" =>         "繃著臉",
-"美术系" =>         "美術系",
-"翘翘板" =>         "翹翹板",
-"耳刮子" =>         "耳刮子",
-"联邦制" =>         "聯邦制",
-"背地里" =>         "背地裡",
-"致良知" =>         "致良知",
-"致远路" =>         "致遠路",
-"台中市" =>         "臺中市",
-"台中县" =>         "臺中縣",
-"台儿庄" =>         "臺兒莊",
-"台东市" =>         "臺東市",
-"台东县" =>         "臺東縣",
-"台柱子" =>         "臺柱子",
-"台机路" =>         "臺機路",
-"舞蹈系" =>         "舞蹈系",
-"航海系" =>         "航海系",
-"航空系" =>         "航空系",
-"航管系" =>         "航管系",
-"英文系" =>         "英文系",
-"范仲淹" =>         "范仲淹",
-"茅台酒" =>         "茅臺酒",
-"蒙汗药" =>         "蒙汗藥",
-"蒲松龄" =>         "蒲松齡",
-"艺术系" =>         "藝術系",
-"药检局" =>         "藥檢局",
-"萤光板" =>         "螢光板",
-"蜡光纸" =>         "蠟光紙",
-"血小板" =>         "血小板",
-"补给线" =>         "補給線",
-"装订线" =>         "裝訂線",
-"复鼎金" =>         "覆鼎金",
-"观光系" =>         "觀光系",
-"讯号线" =>         "訊號線",
-"记分板" =>         "記分板",
-"许可制" =>         "許可制",
-"调理台" =>         "調理台",
-"调频台" =>         "調頻台",
-"誊写板" =>         "謄寫板",
-"警戒线" =>         "警戒線",
-"护理系" =>         "護理系",
-"豆腐干" =>         "豆腐干",
-"贝里斯" =>         "貝里斯",
-"负责制" =>         "負責制",
-"财税系" =>         "財稅系",
-"财管系" =>         "財管系",
-"财金系" =>         "財金系",
-"责任制" =>         "責任制",
-"资管系" =>         "資管系",
-"资讯系" =>         "資訊系",
-"路东里" =>         "路東里",
-"踏脚板" =>         "踏腳板",
-"跷跷板" =>         "蹺蹺板",
-"辅导系" =>         "輔導系",
-"轮机系" =>         "輪機系",
-"农化系" =>         "農化系",
-"农业系" =>         "農業系",
-"农经系" =>         "農經系",
-"农艺系" =>         "農藝系",
-"迴文诗" =>         "迴文詩",
-"迴纹针" =>         "迴紋針",
-"迷幻药" =>         "迷幻藥",
-"迷魂药" =>         "迷魂藥",
-"退烧药" =>         "退燒藥",
-"这夥人" =>         "這夥人",
-"速食面" =>         "速食麵",
-"造船系" =>         "造船系",
-"避孕药" =>         "避孕藥",
-"郡县制" =>         "郡縣制",
-"都计系" =>         "都計系",
-"醋坛子" =>         "醋罈子",
-"医学奖" =>         "醫學獎",
-"医工系" =>         "醫工系",
-"医技系" =>         "醫技系",
-"里斯本" =>         "里斯本",
-"里肌肉" =>         "里肌肉",
-"金像奖" =>         "金像獎",
-"金师奖" =>         "金師獎",
-"金熊奖" =>         "金熊獎",
-"金牌奖" =>         "金牌獎",
-"金球奖" =>         "金球獎",
-"金马奖" =>         "金馬獎",
-"金鼎奖" =>         "金鼎獎",
-"钓鱼台" =>         "釣魚台",
-"银保系" =>         "銀保系",
-"银行系" =>         "銀行系",
-"钟乳石" =>         "鐘乳石",
-"钟鼎文" =>         "鐘鼎文",
-"阿里山" =>         "阿里山",
-"阳春面" =>         "陽春麵",
-"双绞线" =>         "雙絞線",
-"双轨制" =>         "雙軌制",
-"双黄线" =>         "雙黃線",
-"雨花台" =>         "雨花臺",
-"雪里红" =>         "雪裡紅",
-"雪里荭" =>         "雪裡葒",
-"云咸街" =>         "雲咸街",
-"电子系" =>         "電子系",
-"电子表" =>         "電子錶",
-"电机系" =>         "電機系",
-"电源线" =>         "電源線",
-"电算系" =>         "電算系",
-"电视台" =>         "電視台",
-"电话线" =>         "電話線",
-"电路板" =>         "電路板",
-"音乐台" =>         "音樂台",
-"音乐系" =>         "音樂系",
-"音源线" =>         "音源線",
-"风景线" =>         "風景線",
-"食品系" =>         "食品系",
-"马拉松" =>         "馬拉松",
-"马里兰" =>         "馬里蘭",
-"骨子里" =>         "骨子裡",
-"脏兮兮" =>         "髒兮兮",
-"脏东西" =>         "髒東西",
-"体育系" =>         "體育系",
-"高松路" =>         "高松路",
-"魁北克" =>         "魁北克",
-"凤松路" =>         "鳳松路",
-"麦当劳" =>         "麥當勞",
-"麻醉药" =>         "麻醉藥",
-"鼎折足" =>         "鼎折足",
 "一国两制" =>      "一國兩制",
 "一拍即合" =>      "一拍即合",
 "一板一眼" =>      "一板一眼",