qieyun_zaonhe.schema.yaml

# Rime schema
# encoding: utf-8

schema:
  schema_id: qieyun_zaonhe
  name: 推導上海話
  version: "2022.07.05"
  author:
    - Yuanhao 'Nyoeghau' Chen <nyoeghau@nyoeghau.com>
  description: |-
    切韻音系推導上海話：
    https://nk2028.shn.hk/qieyun-autoderiver/
    https://github.com/nk2028/qieyun-examples/blob/main/zaonhe.js

    由上述方案自動生成 IPA，並轉爲吳語協會式拼音。
  dependencies:
    - luna_pinyin

switches:
  - name: ascii_mode
    reset: 0
    states: [中文, 西文]
  - name: half_shape
    states: [全角, 半角]
  - name: simplification
    states: [漢字, 汉字]
  - name: ascii_punct
    states: [。，, ．，]

engine:
  processors:
    - ascii_composer
    - recognizer
    - key_binder
    - speller
    - punctuator
    - selector
    - navigator
    - express_editor
  segmentors:
    - ascii_segmentor
    - matcher
    - affix_segmentor@luna_pinyin
    - abc_segmentor
    - punct_segmentor
    - fallback_segmentor
  translators:
    - punct_translator
    - script_translator
    - script_translator@luna_pinyin
  filters:
    - simplifier
    - uniquifier
    - reverse_lookup_filter@qieyun_zaonhe_reverse_lookup

speller:
  alphabet: zyxwvutsrqponmlkjihgfedcba
  delimiter: " '"
  algebra:
    - xform/5$/x/
    - xform/[1678]$//
    - derive/x$//

    - abbrev/^([a-z]).+$/$1/
    - abbrev/^(([ptsck]|ts)h).+$/$1/
    - abbrev/^(ts).+$/$1/
    - abbrev/^(ny).+$/$1/
    - abbrev/^(ng).+$/$1/
    - abbrev/^(gh).+$/$1/

    - derive/aeh(\d|$)/ah/

    # 兼容吳語學堂
    - derive/^r$/er/
    - abbrev/^nyi(?=[nh]$|$)/gni/
    - abbrev/^ny(?=[aeou])/gni/
    - derive/ui(?=[nh]$)/u/
    - derive/h$/q/

translator:
  dictionary: qieyun_zaonhe
  spelling_hints: 8

luna_pinyin:
  tag: luna_pinyin
  dictionary: luna_pinyin
  prefix: "`"
  suffix: ";"
  tips: 〔普通話〕
  preedit_format:
    - xform/([nl])v/$1ü/
    - xform/([nl])ue/$1üe/
    - xform/([jqxy])v/$1u/

qieyun_zaonhe_reverse_lookup:
  tags: [luna_pinyin]
  overwrite_comment: false
  dictionary: qieyun_zaonhe

punctuator:
  import_preset: symbols

key_binder:
  import_preset: default

recognizer:
  import_preset: default
  patterns:
    punct: "^/([0-9]0?|[a-z]+)$"
    luna_pinyin: "`[a-z]*;?$"