psu-libraries/psulib_blacklight

View on GitHub
solr/conf/mapping-cjkMarcCompatibility.txt

Summary

Maintainability
Test Coverage
# the context of CJK vernacular scripts in bibliographic metadata.
# The list aims to unify searching for equivalent CJK characters that
# may have different Unicode encodings and/or presentation forms based
# on their input methods. It is derived from Princeton University
# Library's "IME variants not present in the EACC/MARC21 character
# sets" (https://library.princeton.edu/projects/eacc/oldindex.htm)
# and the Library of Congress Cataloging Policy and Support Office's
# CJK Compatibility Database (https://www.loc.gov/ils/cjk_search/cjk_cpso.html),
# both of which were created to support the work of catalogers and
# users of CJK scripts in MARC-21 records.

# ‐ => -
"\u2010" => "\u002D"

# 「 => 「
"\uFF62" => "\u300C"

# 」 => 」
"\uFF63" => "\u300D"

# 『 => 「
"\u300E" => "\u300C"

# 』 => 」
"\u300F" => "\u300D"

# < => <
"\uFF1C" => "\u003C"

# 0 => 〇
"\uFF10" => "\u3007"

# 不 => 不
"\uF967" => "\u4E0D"

# 串 => 串
"\uF905" => "\u4E32"

# 丹 => 丹
"\uF95E" => "\u4E39"

# 亂 => 亂
"\uF91B" => "\u4E82"

# 了 => 了
"\uF9BA" => "\u4E86"

# 亮 => 亮
"\uF977" => "\u4EAE"

# 亷 => 廉
"\u4EB7" => "\u5EC9"

# 什 => 什
"\uF9FD" => "\u4EC0"

# 令 => 令
"\uF9A8" => "\u4EE4"

# 來 => 來
"\uF92D" => "\u4F86"

# 例 => 例
"\uF9B5" => "\u4F8B"

# 便 => 便
"\uF965" => "\u4FBF"

# 倫 => 倫
"\uF9D4" => "\u502B"

# 倶 => 俱
"\u5036" => "\u4FF1"

# 僚 => 僚
"\uF9BB" => "\u50DA"

# 兀 => 兀
"\uFA0C" => "\u5140"

# 兩 => 兩
"\uF978" => "\u5169"

# 兪 => 俞
"\u516A" => "\u4FDE"

# 六 => 六
"\uF9D1" => "\u516D"

# 冷 => 冷
"\uF92E" => "\u51B7"

# 凉 => 凉
"\uF979" => "\u51C9"

# 凌 => 凌
"\uF955" => "\u51CC"

# 凜 => 凜
"\uF954" => "\u51DC"

# 切 => 切
"\uFA00" => "\u5207"

# 列 => 列
"\uF99C" => "\u5217"

# 利 => 利
"\uF9DD" => "\u5229"

# 刪 => 删
"\u522A" => "\u5220"

# 刺 => 刺
"\uF9FF" => "\u523A"

# 劉 => 劉
"\uF9C7" => "\u5289"

# 力 => 力
"\uF98A" => "\u529B"

# 劣 => 劣
"\uF99D" => "\u52A3"

# 勒 => 勒
"\uF952" => "\u52D2"

# 勞 => 勞
"\uF92F" => "\u52DE"

# 勵 => 勵
"\uF97F" => "\u52F5"

# 匀 => 勻
"\u5300" => "\u52FB"

# 北 => 北
"\uF963" => "\u5317"

# 匿 => 匿
"\uF9EB" => "\u533F"

# 卵 => 卵
"\uF91C" => "\u5375"

# 參 => 參
"\uF96B" => "\u53C3"

# 句 => 句
"\uF906" => "\u53E5"

# 吏 => 吏
"\uF9DE" => "\u540F"

# 吝 => 吝
"\uF9ED" => "\u541D"

# 呂 => 呂
"\uF980" => "\u5442"

# 咽 => 咽
"\uF99E" => "\u54BD"

# 喇 => 喇
"\uF90B" => "\u5587"

# 囹 => 囹
"\uF9A9" => "\u56F9"

# 圏 => 圈
"\u570F" => "\u5708"

# 塚 => 塚
"\uFA10" => "\u585A"

# 塞 => 塞
"\uF96C" => "\u585E"

# 壘 => 壘
"\uF94A" => "\u58D8"

# 壟 => 壟
"\uF942" => "\u58DF"

# 奈 => 奈
"\uF90C" => "\u5948"

# 契 => 契
"\uF909" => "\u5951"

# 女 => 女
"\uF981" => "\u5973"

# 姫 => 姬
"\u59EB" => "\u59EC"

# 宅 => 宅
"\uFA04" => "\u5B85"

# 宫 => 宮
"\u5BAB" => "\u5BAE"

# 寛 => 寬
"\u5BDB" => "\u5BEC"

# 寧 => 寧
"\uF95F" => "\u5BE7"

# 寧 => 寧
"\uF9AA" => "\u5BE7"

# 寮 => 寮
"\uF9BC" => "\u5BEE"

# 尙 => 尚
"\u5C19" => "\u5C1A"

# 尭 => 堯
"\u5C2D" => "\u582F"

# 尿 => 尿
"\uF9BD" => "\u5C3F"

# 屛 => 摒
"\u5C5B" => "\u6452"

# 屢 => 屢
"\uF94B" => "\u5C62"

# 履 => 履
"\uF9DF" => "\u5C65"

# 崙 => 崙
"\uF9D5" => "\u5D19"

# 嵐 => 嵐
"\uF921" => "\u5D50"

# 嶺 => 嶺
"\uF9AB" => "\u5DBA"

# 巗 => 巖
"\u5DD7" => "\u5DD6"

# 巻 => 卷
"\u5BFD" => "\u5377"

# 巻 => 卷
"\u5DFB" => "\u5377"

# 帲 => 帡
"\u5E32" => "\u5E21"

# 年 => 年
"\uF98E" => "\u5E74"

# 度 => 度
"\uFA01" => "\u5EA6"

# 廉 => 廉
"\uF9A2" => "\u5EC9"

# 廊 => 廊
"\uF928" => "\u5ECA"

# 廓 => 廓
"\uFA0B" => "\u5ED3"

# 廬 => 廬
"\uF982" => "\u5EEC"

# 弄 => 弄
"\uF943" => "\u5F04"

# 彚 => 彙
"\u5F5A" => "\u5F59"

# 律 => 律
"\uF9D8" => "\u5F8B"

# 復 => 復
"\uF966" => "\u5FA9"

# 念 => 念
"\uF9A3" => "\u5FF5"

# 怒 => 怒
"\uF960" => "\u6012"

# 怜 => 怜
"\uF9AC" => "\u601C"

# 惡 => 惡
"\uF9B9" => "\u60E1"

# 慄 => 慄
"\uF9D9" => "\u6144"

# 憐 => 憐
"\uF98F" => "\u6190"

# 懶 => 懶
"\uF90D" => "\u61F6"

# 戀 => 戀
"\uF990" => "\u6200"

# 戮 => 戮
"\uF9D2" => "\u622E"

# 戱 => 戯
"\u6231" => "\u622F"

# 户 => 戶
"\u6237" => "\u6236"

# 戸 => 戶
"\u6238" => "\u6236"

# 拉 => 拉
"\uF925" => "\u62C9"

# 拏 => 拏
"\uF95B" => "\u62CF"

# 拓 => 拓
"\uFA02" => "\u62D3"

# 拾 => 拾
"\uF973" => "\u62FE"

# 捻 => 捻
"\uF9A4" => "\u637B"

# 掠 => 掠
"\uF975" => "\u63A0"

# 揅 => 研
"\u63C5" => "\u7814"

# 揑 => 捏
"\u63D1" => "\u634F"

# 揷 => 挿
"\u63F7" => "\u633F"

# 揺 => 摇
"\u63FA" => "\u6447"

# 撚 => 撚
"\uF991" => "\u649A"

# 敍 => 敘
"\u654D" => "\u6558"

# 數 => 數
"\uF969" => "\u6578"

# 料 => 料
"\uF9BE" => "\u6599"

# 旅 => 旅
"\uF983" => "\u65C5"

# 易 => 易
"\uF9E0" => "\u6613"

# 昻 => 昂
"\u663B" => "\u6602"

# 晩 => 晚
"\u6669" => "\u665A"

# 晴 => 晴
"\uFA12" => "\u6674"

# 暈 => 暈
"\uF9C5" => "\u6688"

# 暴 => 暴
"\uFA06" => "\u66B4"

# 曆 => 曆
"\uF98B" => "\u66C6"

# 更 => 更
"\uF901" => "\u66F4"

# 朗 => 朗
"\uF929" => "\u6717"

# 李 => 李
"\uF9E1" => "\u674E"

# 杻 => 杻
"\uF9C8" => "\u677B"

# 林 => 林
"\uF9F4" => "\u6797"

# 柳 => 柳
"\uF9C9" => "\u67F3"

# 査 => 查
"\u67FB" => "\u67E5"

# 栗 => 栗
"\uF9DA" => "\u6817"

# 梁 => 梁
"\uF97A" => "\u6881"

# 梨 => 梨
"\uF9E2" => "\u68A8"

# 樂 => 樂
"\uF914" => "\u6A02"

# 樂 => 樂
"\uF95C" => "\u6A02"

# 樂 => 樂
"\uF9BF" => "\u6A02"

# 樓 => 樓
"\uF94C" => "\u6A13"

# 櫓 => 櫓
"\uF931" => "\u6AD3"

# 欄 => 欄
"\uF91D" => "\u6B04"

# 歩 => 步
"\u6B69" => "\u6B65"

# 歳 => 歲
"\u6B73" => "\u6B72"

# 歷 => 歷
"\uF98C" => "\u6B77"

# 殮 => 殮
"\uF9A5" => "\u6BAE"

# 殺 => 殺
"\uF970" => "\u6BBA"

# 毎 => 每
"\u6BCE" => "\u6BCF"

# 汚 => 污
"\u6C5A" => "\u6C61"

# 沈 => 沈
"\uF972" => "\u6C88"

# 沨 => 渢
"\u6CA8" => "\u6E22"

# 泌 => 泌
"\uF968" => "\u6CCC"

# 泥 => 泥
"\uF9E3" => "\u6CE5"

# 洛 => 洛
"\uF915" => "\u6D1B"

# 洞 => 洞
"\uFA05" => "\u6D1E"

# 流 => 流
"\uF9CA" => "\u6D41"

# 浪 => 浪
"\uF92A" => "\u6D6A"

# 淋 => 淋
"\uF9F5" => "\u6DCB"

# 淚 => 淚
"\uF94D" => "\u6DDA"

# 淪 => 淪
"\uF9D6" => "\u6DEA"

# 渉 => 涉
"\u6E09" => "\u6D89"

# 溜 => 溜
"\uF9CB" => "\u6E9C"

# 溺 => 溺
"\uF9EC" => "\u6EBA"

# 滑 => 滑
"\uF904" => "\u6ED1"

# 漏 => 漏
"\uF94E" => "\u6F0F"

# 漣 => 漣
"\uF992" => "\u6F23"

# 潊 => 潊
"\u6F4A" => "\u6F35"

# 濫 => 濫
"\uF922" => "\u6FEB"

# 濵 => 濱
"\u6FF5" => "\u6FF1"

# 濾 => 濾
"\uF984" => "\u6FFE"

# 炙 => 炙
"\uF9FB" => "\u7099"

# 烈 => 烈
"\uF99F" => "\u70C8"

# 烙 => 烙
"\uF916" => "\u70D9"

# 煉 => 煉
"\uF993" => "\u7149"

# 煕 => 熙
"\u7155" => "\u7199"

# 燎 => 燎
"\uF9C0" => "\u71CE"

# 燐 => 燐
"\uF9EE" => "\u71D0"

# 爐 => 爐
"\uF932" => "\u7210"

# 爛 => 爛
"\uF91E" => "\u721B"

# 爲 => 為
"\u7232" => "\u70BA"

# 牢 => 牢
"\uF946" => "\u7262"

# 狀 => 狀
"\uF9FA" => "\u72C0"

# 狼 => 狼
"\uF92B" => "\u72FC"

# 猪 => 猪
"\uFA16" => "\u732A"

# 獵 => 獵
"\uF9A7" => "\u7375"

# 率 => 率
"\uF961" => "\u7387"

# 率 => 率
"\uF9DB" => "\u7387"

# 玲 => 玲
"\uF9AD" => "\u73B2"

# 珞 => 珞
"\uF917" => "\u73DE"

# 理 => 理
"\uF9E4" => "\u7406"

# 琉 => 琉
"\uF9CC" => "\u7409"

# 瑩 => 瑩
"\uF9AE" => "\u7469"

# 瑶 => 瑤
"\u7476" => "\u7464"

# 璉 => 璉
"\uF994" => "\u7489"

# 璘 => 璘
"\uF9EF" => "\u7498"

# 甁 => 瓶
"\u7501" => "\u74F6"

# 留 => 留
"\uF9CD" => "\u7559"

# 略 => 略
"\uF976" => "\u7565"

# 異 => 異
"\uF962" => "\u7570"

# 痢 => 痢
"\uF9E5" => "\u7500"

# 療 => 療
"\uF9C1" => "\u7642"

# 癩 => 癩
"\uF90E" => "\u7669"

# 益 => 益
"\uFA17" => "\u76CA"

# 盧 => 盧
"\uF933" => "\u76E7"

# 省 => 省
"\uF96D" => "\u7701"

# 硫 => 硫
"\uF9CE" => "\u786B"

# 碌 => 碌
"\uF93B" => "\u788C"

# 磊 => 磊
"\uF947" => "\u78CA"

# 磻 => 磻
"\uF964" => "\u78FB"

# 礪 => 礪
"\uF985" => "\u792A"

# 礼 => 礼
"\uFA18" => "\u793C"

# 神 => 神
"\uFA19" => "\u795E"

# 祥 => 祥
"\uFA1A" => "\u7965"

# 祿 => 祿
"\uF93C" => "\u797F"

# 福 => 福
"\uFA1B" => "\u798F"

# 禮 => 禮
"\uF9B6" => "\u79AE"

# 秊 => 秊
"\uF995" => "\u79CA"

# 税 => 稅
"\u7A0E" => "\u7A05"

# 稜 => 稜
"\uF956" => "\u7A1C"

# 立 => 立
"\uF9F7" => "\u7ACB"

# 笠 => 笠
"\uF9F8" => "\u7B20"

# 簾 => 簾
"\uF9A6" => "\u7C3E"

# 籠 => 籠
"\uF944" => "\u7C60"

# 粒 => 粒
"\uF9F9" => "\u7C92"

# 粵 => 粤
"\u7CB5" => "\u7CA4"

# 精 => 精
"\uFA1D" => "\u7CBE"

# 糖 => 糖
"\uFA03" => "\u7CD6"

# 糧 => 糧
"\uF97B" => "\u7CE7"

# 紐 => 紐
"\uF9CF" => "\u7D10"

# 索 => 索
"\uF96A" => "\u7D22"

# 累 => 累
"\uF94F" => "\u7D2F"

# 綠 => 綠
"\uF93D" => "\u7DA0"

# 綾 => 綾
"\uF957" => "\u7DBE"

# 緃 => 縱
"\u7DC3" => "\u7E31"

# 緒 => 緖
"\u7DD2" => "\u7DD6"

# 練 => 練
"\uF996" => "\u7DF4"

# 縷 => 縷
"\uF950" => "\u7E37"

# 繋 => 繫
"\u7E4B" => "\u7E6B"

# 繍 => 繡
"\u7E4D" => "\u7E61"

# 罹 => 罹
"\uF9E6" => "\u7F79"

# 羅 => 羅
"\uF90F" => "\u7F85"

# 羚 => 羚
"\uF9AF" => "\u7F9A"

# 羽 => 羽
"\uFA1E" => "\u7FBD"

# 老 => 老
"\uF934" => "\u8001"

# 聆 => 聆
"\uF9B0" => "\u8046"

# 聯 => 聯
"\uF997" => "\u806F"

# 聾 => 聾
"\uF945" => "\u807E"

# 肋 => 肋
"\uF953" => "\u808B"

# 脱 => 脫
"\u8131" => "\u812B"

# 臘 => 臘
"\uF926" => "\u81D8"

# 臨 => 臨
"\uF9F6" => "\u81E8"

# 良 => 良
"\uF97C" => "\u826F"

# 若 => 若
"\uF974" => "\u82E5"

# 茶 => 茶
"\uF9FE" => "\u8336"

# 荆 => 荊
"\u8346" => "\u834A"

# 菉 => 菉
"\uF93E" => "\u83C9"

# 菱 => 菱
"\uF958" => "\u83F1"

# 落 => 落
"\uF918" => "\u843D"

# 葉 => 葉
"\uF96E" => "\u8449"

# 蓮 => 蓮
"\uF999" => "\u84EE"

# 蓼 => 蓼
"\uF9C2" => "\u84FC"

# 薫 => 薰
"\u85AB" => "\u85B0"

# 藍 => 藍
"\uF923" => "\u85CD"

# 藺 => 藺
"\uF9F0" => "\u85FA"

# 蘆 => 蘆
"\uF935" => "\u8606"

# 蘭 => 蘭
"\uF91F" => "\u862D"

# 蘿 => 蘿
"\uF910" => "\u863F"

# 虚 => 虛
"\u865A" => "\u865B"

# 虜 => 虜
"\uF936" => "\u865C"

# 螺 => 螺
"\uF911" => "\u87BA"

# 﨑 => 崎
"\uFA11" => "\u5D0E"

# 蠟 => 蠟
"\uF927" => "\u881F"

# 行 => 行
"\uFA08" => "\u884C"

# 裂 => 裂
"\uF9A0" => "\u88C2"

# 裏 => 裏
"\uF9E7" => "\u88CF"

# 裡 => 裡
"\uF9E8" => "\u88E1"

# 裵 => 裴
"\u88F5" => "\u88F4"

# 裸 => 裸
"\uF912" => "\u88F8"

# 襤 => 襤
"\uF924" => "\u8964"

# 見 => 見
"\uFA0A" => "\u898B"

# 說 => 說
"\uF96F" => "\u8AAA"

# 說 => 說
"\uF9A1" => "\u8AAA"

# 説 => 說
"\u8AAC" => "\u8AAA"

# 諒 => 諒
"\uF97D" => "\u8AD2"

# 論 => 論
"\uF941" => "\u8AD6"

# 諸 => 諸
"\uFA22" => "\u8AF8"

# 諾 => 諾
"\uF95D" => "\u8AFE"

# 識 => 識
"\uF9FC" => "\u8B58"

# 讀 => 讀
"\uF95A" => "\u8B80"

# 豈 => 豈
"\uF900" => "\u8C48"

# 賂 => 賂
"\uF948" => "\u8CC2"

# 賈 => 賈
"\uF903" => "\u8CC8"

# 路 => 路
"\uF937" => "\u8DEF"

# 車 => 車
"\uF902" => "\u8ECA"

# 輦 => 輦
"\uF998" => "\u8F26"

# 輪 => 輪
"\uF9D7" => "\u8F2A"

# 輻 => 輻
"\uFA07" => "\u8F3B"

# 轢 => 轢
"\uF98D" => "\u8F62"

# 辰 => 辰
"\uF971" => "\u8FB0"

# 連 => 連
"\uF99A" => "\u9023"

# 逸 => 逸
"\uFA25" => "\u9038"

# 遼 => 遼
"\uF9C3" => "\u907C"

# 邏 => 邏
"\uF913" => "\u908F"

# 郎 => 郎
"\uF92C" => "\u90CE"

# 郞 => 郎
"\u90DE" => "\u90CE"

# 郷 => 鄉
"\u90F7" => "\u9109"

# 都 => 都
"\uFA26" => "\u90FD"

# 鄕 => 鄉
"\u9115" => "\u9109"

# 酪 => 酪
"\uF919" => "\u916A"

# 醴 => 醴
"\uF9B7" => "\u91B4"

# 里 => 里
"\uF9E9" => "\u91CC"

# 量 => 量
"\uF97E" => "\u91CF"

# 金 => 金
"\uF90A" => "\u91D1"

# 鈴 => 鈴
"\uF9B1" => "\u9234"

# 鋭 => 銳
"\u92ED" => "\u92B3"

# 錄 => 錄
"\uF93F" => "\u9304"

# 録 => 錄
"\u9332" => "\u9304"

# 鍊 => 鍊
"\uF99B" => "\u934A"

# 鎸 => 鐫
"\u93B8" => "\u942B"

# 鐠 => 镨
"\u9420" => "\u9568"

# 閭 => 閭
"\uF986" => "\u95AD"

# 閲 => 閱
"\u95B2" => "\u95B1"

# 闗 => 關
"\u95D7" => "\u95DC"

# 阮 => 阮
"\uF9C6" => "\u962E"

# 陃 => 隣
"\u9643" => "\u96A3"

# 陋 => 陋
"\uF951" => "\u964B"

# 降 => 降
"\uFA09" => "\u964D"

# 陵 => 陵
"\uF959" => "\u9675"

# 陸 => 陸
"\uF9D3" => "\u9678"

# 隆 => 隆
"\uF9DC" => "\u9686"

# 鄰 => 隣
"\u9310" => "\u96A3"

# 隣 => 隣
"\uF9F1" => "\u96A3"

# 隸 => 隸
"\uF9B8" => "\u96B8"

# 離 => 離
"\uF9EA" => "\u9600"

# 零 => 零
"\uF9B2" => "\u96F6"

# 雷 => 雷
"\uF949" => "\u96F7"

# 露 => 露
"\uF938" => "\u9732"

# 靈 => 靈
"\uF9B3" => "\u9748"

# 靖 => 靖
"\uFA1C" => "\u9756"

# 領 => 領
"\uF9B4" => "\u9818"

# 頻 => 頻
"\uFA6A" => "\u983B"

# 類 => 類
"\uF9D0" => "\u985E"

# 飯 => 飯
"\uFA2A" => "\u98EF"

# 飲 => 飮
"\u98F2" => "\u98EE"

# 飼 => 飼
"\uFA2B" => "\u98FC"

# 館 => 館
"\uFA2C" => "\u9928"

# 駱 => 駱
"\uF91A" => "\u99F1"

# 騨 => 驒
"\u9A28" => "\u9A52"

# 驪 => 驪
"\uF987" => "\u9A6A"

# 髙 => 高
"\u9AD9" => "\u9AD8"

# 魯 => 魯
"\uF939" => "\u9B6F"

# 鱗 => 鱗
"\uF9F2" => "\u9C57"

# 鶴 => 鶴
"\uFA2D" => "\u9DB4"

# 鷺 => 鷺
"\uF93A" => "\u9DFA"

# 鸞 => 鸞
"\uF920" => "\u9E1E"

# 鹿 => 鹿
"\uF940" => "\u9E7F"

# 麗 => 麗
"\uF988" => "\u9E97"

# 麟 => 麟
"\uF9F3" => "\u9E9F"

# 麹 => 麴
"\u9EB9" => "\u9EB4"

# 黎 => 黎
"\uF989" => "\u9ECE"

# 龍 => 龍
"\uF9C4" => "\u9F8D"

# 龜 => 龜
"\uF907" => "\u9F9C"

# 龜 => 龜
"\uF908" => "\u9F9C"