廣韻反查

middle_chinese_lookup.schema.yaml

# Rime schema
# encoding: utf-8

schema:
  schema_id: middle_chinese_lookup
  name: 廣韻查詢
  version: "2.2"
  author:
    - Polyhedron
    - 雪齋
    - 佛振
  description:
    基於Polyhedron製作的中古漢語拼音（亦稱「古韻羅馬字」）製作
    韻典網·廣韻 http://ytenx.org/kyonh/
    http://zh.wikipedia.org/wiki/User:Polyhedron/中古漢語拼音
    雪齋在此基礎上寫出反算廣韻漢字聲韻調算法
    顯示結果爲：「〖聲母〗介音【韻母】聲調」
    韻母皆舉平以賅上去入，脣音無開合，分重紐
    聲母可選是否區分輕重脣音，聲調可選是否區分陰陽
  dependencies:
    - zyenpheng
    - cangjie5
    - luna_pinyin

switches:
  - name: ascii_mode
    reset: 0
    states: [ 中文, 西文 ]
  - name: full_shape
    reset: 0
    states: [ 半角, 全角 ]

engine:
  processors:
    - ascii_composer
    - recognizer
    - key_binder
    - speller
    - punctuator
    - selector
    - navigator
    - express_editor
  segmentors:
    - ascii_segmentor
    - matcher
    - affix_segmentor@pinyin
    - affix_segmentor@cangjie
    - affix_segmentor@reverse_lookup
    - abc_segmentor
    - punct_segmentor
    - fallback_segmentor
  translators:
    - echo_translator
    - punct_translator
    - script_translator@zyenpheng
    - table_translator@cangjie
    - script_translator@pinyin
  filters:
    - reverse_lookup_filter@middle_chinese_lookup
    - uniquifier

speller:
  alphabet: 'zyxwvutsrqponmlkjihgfedcba'
  delimiter: " '"

# 中古全拼
abc_segmentor:
  extra_tags: [ zyenpheng, cangjie ]

zyenpheng:
  # table_translator@zyenpheng
  dictionary: zyenpheng
  spelling_hints: 4
  preedit_format:
    - "xform/^([a-z]*)$/【廣韻】$1/"

# 用倉頡輸入，加前綴C:
cangjie:
  # table_translator@cangjie
  dictionary: cangjie5
  enable_charset_filter: true
  preedit_format:
    - 'xform/^([a-z]*)$/【廣韻】$1｜\U$1\E/'
    - "xlit|ABCDEFGHIJKLMNOPQRSTUVWXYZ|日月金木水火土竹戈十大中一弓人心手口尸廿山女田難卜符|"
  comment_format:
    - "xlit|abcdefghijklmnopqrstuvwxyz'~|日月金木水火土竹戈十大中一弓人心手口尸廿山女田難卜符·～|"
  # affix_segmentor@cangjie
  tag: cangjie
  prefix: 'C:'
  suffix: ';'
  tips: 〔倉頡〕
  closing_tips: 〔廣韻〕

# 用漢語拼音輸入，加前綴P:
pinyin:
  # script_translator@pinyin
  dictionary: luna_pinyin
  preedit_format:
    - "xform/^([a-z]*)$/【廣韻】$1/"
  # affix_segmentor@pinyin
  tag: pinyin
  prefix: 'P:'
  suffix: ';'
  tips: 〔拼音〕
  closing_tips: 〔廣韻〕

# 用倉頡或拼音反查，加前綴:
# affix_segmentor@reverse_lookup
reverse_lookup:
  tag: reverse_lookup
  extra_tags: [ cangjie, pinyin ]
  prefix: ':'
  suffix: ';'
  tips: 〔反查〕
  closing_tips: 〔廣韻〕

key_binder:
  import_preset: default

punctuator:
  import_preset: default

recognizer:
  import_preset: default
  patterns:
    cangjie: "C:[a-z']*;?$"
    pinyin: "P:[a-z']*;?$"
    reverse_lookup: "(?<![A-Z]):[a-z']*;?$"

# 標註中古音
middle_chinese_lookup:
  tags:  # any
  dictionary: zyenpheng
  overwrite_comment: true  # 覆蓋其他提示
  comment_format:
# 同時顯示羅馬字拼寫
    - "xform/^(.*)$/\x01$1\x03\x04($1)/"
    - "xform/ (?=.*\x04)/\x03 \x01/"
# 預處理
    - "xform/ng(?=.*\x04)/ŋ/"
    - "xform/k\x03/ŋq\x03/"
    - "xform/t\x03/nq\x03/"
    - "xform/p\x03/mq\x03/"
    - "xform/(\x01(?:th?|ch?|zs?|[dns]))r(?=[^iy'])/$1r'r/"
    - "xform/(\x01(?:ph?|kh?|gh?|[bmhqjiy]|ŋ)[iy])eŋ/$1æŋ/"
    - "xform/j(?![iy'])(?=.*\x04)/ji/"
    - "xform/(\x01(?:ch?|zs?|[sn])?[jl])(?=([iy]e([umn]|ŋ)?|i[imn]|yn)[dxhq]?)/$1'j/"
    - "xform/(\x01(?:ch?|zs?|s))(?=(?:[iy]e(?:[umn]|ŋ)?|i[imn]|yn)[dxhq]?)/$1'j/"
    - "xform/(\x01(?:ch?|zs?|s)rj?i)n/$1ɿn/"
    - "xform/(\x01)(?!ph?|kh?|gh?|ŋ|[bmhqjiy])([^aeiouy]*y)n([xhq]?\x03)/$1$2ɿn$3/"
    - "xform/(\x01)([^aeiouy]*jy)n([xhq]?\x03)/$1$2ɿn$3/"
    - "xform/(\x01)(?!kh?|g|ŋ)([^aeioux]*)ia([xhq]?\x03)/$1$2'ria$3/"
# 合併不同聲調
    - "xform/([^xhdq])\x03/$1w\x03/"
    - xform/(\x01[^\x01\x03]+)([whxq])\x03((?:\s\x01[^\x01\x03]+\x03)*)\s\1([whxq])\x03((?:\s\x01[^\x01\x03]+\x03)*)\s\1([whxq]\x03)/$1$2$4$6$3$5/
    - xform/(\x01[^\x01\x03]+)([whxq])\x03((?:\s\x01[^\x01\x03]+\x03)*)\s\1([whxq]\x03)/$1$2$4$3/
# 轉化聲母
#    - "xform/\x01ph(?=y(o[in]?|a[mnd]|[au]ŋ)|iu(ŋ)?)/N\x01L敷\x02/"
#    - "xform/\x01p(?=y(o[in]?|a[mnd]|[au]ŋ)|iu(ŋ)?)/N\x01L非\x02/"
#    - "xform/\x01b(?=y(o[in]?|a[mnd]|[au]ŋ)|iu(ŋ)?)/P\x01L奉\x02/"
#    - "xform/\x01m(?=y(o[in]?|a[mnd]|[au]ŋ))/P\x01L微\x02/"
    - "xform/\x01ph/N\x01L滂\x02/"
    - "xform/\x01p/N\x01L幫\x02/"
    - "xform/\x01b/P\x01L並\x02/"
    - "xform/\x01m/P\x01L明\x02/"
    - "xform/\x01thr/N\x01徹\x02/"
    - "xform/\x01tr/N\x01知\x02/"
    - "xform/\x01dr/P\x01澄\x02/"
    - "xform/\x01nr/P\x01孃\x02/"
    - "xform/\x01nj/P\x01日\x02/"
    - "xform/\x01th/N\x01透\x02/"
    - "xform/\x01t/N\x01端\x02/"
    - "xform/\x01d/P\x01定\x02/"
    - "xform/\x01n/P\x01泥\x02/"
    - "xform/\x01chr/N\x01初\x02/"
    - "xform/\x01cr/N\x01莊\x02/"
    - "xform/\x01zsr/P\x01俟\x02/"
    - "xform/\x01zr/P\x01崇\x02/"
    - "xform/\x01sr/N\x01生\x02/"
    - "xform/\x01ch(j)/N\x01昌\x02/"
    - "xform/\x01c(j)/N\x01章\x02/"
    - "xform/\x01zs(j)/P\x01船\x02/"
    - "xform/\x01z(j)/P\x01常\x02/"
    - "xform/\x01s(j)/N\x01書\x02/"
    - "xform/\x01ch/N\x01清\x02/"
    - "xform/\x01c/N\x01精\x02/"
    - "xform/\x01zs/P\x01邪\x02/"
    - "xform/\x01z/P\x01從\x02/"
    - "xform/\x01s/N\x01心\x02/"
    - "xform/\x01kh/N\x01谿\x02/"
    - "xform/\x01k/N\x01見\x02/"
    - "xform/\x01gh/P\x01匣\x02/"
    - "xform/\x01g/P\x01羣\x02/"
    - "xform/\x01ŋ/P\x01疑\x02/"
    - "xform/\x01h/N\x01曉\x02/"
    - "xform/\x01q/N\x01影\x02/"
    - "xform/\x01([iy])/P\x01云\x02$1/"
    - "xform/\x01j/P\x01以\x02/"
    - "xform/\x01l/P\x01來\x02/"
    - "xform/'//"
# 合併不同聲母
    - xform/([NP])\x01(L?)([^\x00-\x7f]{3})\x02([^\x01\x02\x03wxhq]+)([wxhq]+)\x03\s((?:[NP]\x01[^\x01\x03]+\x03\s)*)([NP])\x01\2([^\x00-\x7f]{3})\x02\4([wxhq]+\x03)/$1$7\x01$2$3／$8\x02$4$5／$9 $6/
# 轉化韻母
    - "xform/\x02(i?)uŋ((?:[wxhq]|／)*\x03)/\x02$1東$2/"
    - "xform/\x02(y)uŋ((?:[wxhq]|／)*\x03)/\x02$1鐘$2/"
    - "xform/\x02(u)uŋ((?:[wxhq]|／)*\x03)/\x02$1冬$2/"
    - "xform/\x02(r)uŋ((?:[wxhq]|／)*\x03)/\x02$1江$2/"
    - "xform/\x02([iy])aŋ((?:[wxhq]|／)*\x03)/\x02$1o陽$2/"
    - "xform/\x02(u?)aŋ((?:[wxhq]|／)*\x03)/\x02$1o唐$2/"
    - "xform/\x02(ru?)aŋ((?:[wxhq]|／)*\x03)/\x02$1o庚$2/"
    - "xform/\x02([iy])æŋ((?:[wxhq]|／)*\x03)/\x02ɨ$1o庚$2/"
    - "xform/\x02(ru?)eŋ((?:[wxhq]|／)*\x03)/\x02$1o耕$2/"
    - "xform/\x02j?([iy])eŋ((?:[wxhq]|／)*\x03)/\x02jɨ$1o清$2/"
    - "xform/\x02(u?e)ŋ((?:[wxhq]|／)*\x03)/\x02$1o青$2/"
    - "xform/\x02([iy])ŋ((?:[wxhq]|／)*\x03)/\x02$1o蒸$2/"
    - "xform/\x02(u?)oŋ((?:[wxhq]|／)*\x03)/\x02$1o登$2/"
 
    - "xform/\x02(j?)(y)ɿn((?:[wxhq]|／)*\x03)/\x02$1ɨ$2o諄$3/"
    - "xform/\x02(j?)(i)ɿn((?:[wxhq]|／)*\x03)/\x02$1ɨ$2o臻$3/"
    - "xform/\x02(j?)([iy])n((?:[wxhq]|／)*\x03)/\x02$1ɨ$2o眞$3/"
    - "xform/\x02(i)on((?:[wxhq]|／)*\x03)/\x02$1o欣$2/"
    - "xform/\x02(u)on((?:[wxhq]|／)*\x03)/\x02$1o魂$2/"
    - "xform/\x02on((?:[wxhq]|／)*\x03)/\x02o痕$1/"
    - "xform/\x02(y)on((?:[wxhq]|／)*\x03)/\x02$1o文$2/"
    - "xform/\x02(u)an((?:[wxhq]|／)*\x03)/\x02$1o桓$2/"
    - "xform/\x02([iy])an((?:[wxhq]|／)*\x03)/\x02$1o元$2/"
    - "xform/\x02(ru?)an((?:[wxhq]|／)*\x03)/\x02$1o刪$2/"
    - "xform/\x02an((?:[wxhq]|／)*\x03)/\x02o寒$1/"
    - "xform/\x02(ru?)en((?:[wxhq]|／)*\x03)/\x02$1o山$2/"
    - "xform/\x02(j?)([iy])en((?:[wxhq]|／)*\x03)/\x02$1ɨ$2o仙$3/"
    - "xform/\x02(u?e)n((?:[wxhq]|／)*\x03)/\x02$1o先$2/"
 
    - "xform/\x02(j?)(i)m((?:[wxhq]|／)*\x03)/\x02$1ɨ$2o侵$3/"
    - "xform/\x02(i)am((?:[wxhq]|／)*\x03)/\x02$1o嚴$2/"
    - "xform/\x02(y)am((?:[wxhq]|／)*\x03)/\x02$1o凡$2/"
    - "xform/\x02(r)am((?:[wxhq]|／)*\x03)/\x02$1o銜$2/"
    - "xform/\x02(r)em((?:[wxhq]|／)*\x03)/\x02$1o咸$2/"
    - "xform/\x02am((?:[wxhq]|／)*\x03)/\x02o談$1/"
    - "xform/\x02(j?)(i)em((?:[wxhq]|／)*\x03)/\x02$1ɨ$2o鹽$3/"
    - "xform/\x02(e)m((?:[wxhq]|／)*\x03)/\x02$1o添$2/"
    - "xform/\x02om((?:[wxhq]|／)*\x03)/\x02o覃$1/"
 
    - "xform/\x02(r)au((?:[wxh]|／)*\x03)/\x02$1肴$2/"
    - "xform/\x02au((?:[wxh]|／)*\x03)/\x02豪$1/"
    - "xform/\x02(j?)(i)eu((?:[wxh]|／)*\x03)/\x02$1ɨ$2宵$3/"
    - "xform/\x02(e)u((?:[wxh]|／)*\x03)/\x02$1蕭$2/"
    - "xform/\x02(i)u((?:[wxh]|／)*\x03)/\x02$1尤$2/"
    - "xform/\x02u((?:[wxh]|／)*\x03)/\x02侯$1/"
    - "xform/\x02(y)((?:[wxh]|／)*\x03)/\x02$1幽$2/"
 
    - "xform/\x02(j?)([iy])e((?:[wxh]|／)*\x03)/\x02$1ɨ$2o支$3/"
    - "xform/\x02(j?)([iy])i((?:[wxh]|／)*\x03)/\x02$1ɨ$2o脂$3/"
    - "xform/\x02i((?:[wxh]|／)*\x03)/\x02o之$1/"
    - "xform/\x02([iy])oi((?:[wxh]|／)*\x03)/\x02$1o微$2/"
    - "xform/\x02([iy])a(d\x03)/\x02$1o廢$2/"
    - "xform/\x02(ru?)a(d\x03)/\x02$1o夬$2/"
    - "xform/\x02(u?)a(d\x03)/\x02$1o泰$2/"
    - "xform/\x02(j?)([iy])e(d\x03)/\x02$1ɨ$2o祭$3/"
    - "xform/\x02(ru?)e((?:[wxh]|／)*\x03)/\x02$1o佳$2/"
    - "xform/\x02(ru?)ai((?:[wxh]|／)*\x03)/\x02$1o皆$2/"
    - "xform/\x02(u?e)((?:[wxh]|／)*\x03)/\x02$1o齊$2/"
    - "xform/\x02i?(u)ai((?:[wxh]|／)*\x03)/\x02$1o灰$2/"
    - "xform/\x02ai((?:[wxh]|／)*\x03)/\x02o咍$1/"
 
    - "xform/\x02([uiy])a((?:[wxh]|／)*\x03)/\x02$1o戈$2/"
    - "xform/\x02a((?:[wxh]|／)*\x03)/\x02o歌$1/"
    - "xform/\x02j?(r[ui]?)a((?:[wxh]|／)*\x03)/\x02$1o麻$2/"
    - "xform/\x02(i)o((?:[wxh]|／)*\x03)/\x02$1魚$2/"
    - "xform/\x02(y)o((?:[wxh]|／)*\x03)/\x02$1虞$2/"
    - "xform/\x02o((?:[wxh]|／)*\x03)/\x02模$1/"
# 調整陰陽調標識
    - "xform/([NP])([NP])?(\x01[^\x01\x03wdxhq]+)([whxqd]+)(?:(／)([whxqd]+))?\x03/$3】$1$4$5$2$6/"
    - xform/\x02([^\x01\x02\x03NPwxhq]+)([NPwxhq]+)／\2/\x02$1$2/
# 轉寫等
    - "xform/\x01(L?)((?:[^\x00-\x7f]{3}|／)+)\x02(j?ɨ)([iy])(o?)([^\x00-\x7f]{3})/〖$2〗重紐$3等\x01$1$5$4\x03【$6/"
    - "xform/\x01(L?)((?:[^\x00-\x7f]{3}|／)+)\x02(u?)e(o?)([^\x00-\x7f]{3})/〖$2〗四等\x01$1$4$3\x03【$5/"
    - "xform/\x01(L?)((?:[^\x00-\x7f]{3}|／)+)\x02r(u?)(o?)([^\x00-\x7f]{3})/〖$2〗二等\x01$1$4$3\x03【$5/"
    - "xform/\x01(L?)((?:[^\x00-\x7f]{3}|／)+)\x02r?([iy])(o?)([^\x00-\x7f]{3})/〖$2〗三等\x01$1$4$3\x03【$5/"
    - "xform/\x01(L?)((?:[^\x00-\x7f]{3}|／)+)\x02(u?)(o?)([^\x00-\x7f]{3})/〖$2〗一等\x01$1$4$3\x03【$5/"
    - "xform/jɨ/四/"
    - "xform/ɨ/三/"
    - "xform/\x01(?!L)o[uy]\x03/合/"
    - "xform/\x01(?!L)oi?\x03/開/"
    - "xform/\x01L?[a-z]*\x03//"
# 轉寫聲調
    - "xform/N//"
    - "xform/P//"
    - "xform/([wxhdq]+)(?=.*\x04)/\\U$1\\E/"
    - "xform/([XHQ]+)W/W$1/"
    - "xform/(W?)([HQ]+)X/$1X$2/"
    - "xform/QH/HQ/"
    - "xlit|WXHDQ|平上去去入|"
    - "xform/\x04/  /"