refactor: 改写拼写规则的搭桥字母 (#332)

2023-06-08 06:42:01 +08:00 · 2023-06-08 06:42:01 +08:00 · 8b4b8d49a7
commit 8b4b8d49a7
parent cb56778fee
14 changed files with 134 additions and 152 deletions
--- a/cn_dicts/others.dict.yaml
+++ b/cn_dicts/others.dict.yaml
@ -12,33 +12,32 @@ version: "2023-04-08"
 sort: by_weight
 ...
 ##### 大写字母
-# 因为默认的双拼拼写规则用掉了大写字母。这些奇怪的编码是为了做 xlit 转写，同时适配全拼和双拼。
-A	ā
-B	ḃ
-C	ç
-D	ď
-E	ē
-F	ḟ
-G	ḡ
-H	ĥ
-I	ī
-J	ĵ
-K	ḱ
-L	ĺ
-M	ḿ
-N	ń
-O	ō
-P	ṕ
-Q	ɋ
-R	ŕ
-S	ś
-T	ť
-U	ū
-V	ṽ
-W	ẃ
-X	ẋ
-Y	ȳ
-Z	ź
+A	A
+B	B
+C	C
+D	D
+E	E
+F	F
+G	G
+H	H
+I	I
+J	J
+K	K
+L	L
+M	M
+N	N
+O	O
+P	P
+Q	Q
+R	R
+S	S
+T	T
+U	U
+V	V
+W	W
+X	X
+Y	Y
+Z	Z

 ##### 容错词
 # 「血xue、xie」「谁shui、shei」「露lu、lou」「熟shu、shou」「密钥yao、yue」已在 base 中实现
--- a/double_pinyin.schema.yaml
+++ b/double_pinyin.schema.yaml
@ -237,32 +237,30 @@ speller:
    - derive/^([jqxy])u$/$1v/
    - derive/^([aoe])([ioun])$/$1$1$2/
    - xform/^([aoe])(ng)?$/$1$1$2/
-    - xform/iu$/Q/
-    - xform/[iu]a$/W/
-    - xform/[uv]an$/R/
-    - xform/[uv]e$/T/
-    - xform/ing$|uai$/Y/
-    - xform/^sh/U/
-    - xform/^ch/I/
-    - xform/^zh/V/
-    - xform/uo$/O/
-    - xform/[uv]n$/P/
-    - xform/i?ong$/S/
-    - xform/[iu]ang$/D/
-    - xform/(.)en$/$1F/
-    - xform/(.)eng$/$1G/
-    - xform/(.)ang$/$1H/
-    - xform/ian$/M/
-    - xform/(.)an$/$1J/
-    - xform/iao$/C/
-    - xform/(.)ao$/$1K/
-    - xform/(.)ai$/$1L/
-    - xform/(.)ei$/$1Z/
-    - xform/ie$/X/
-    - xform/ui$/V/
-    - xform/(.)ou$/$1B/
-    - xform/in$/N/
-    - xlit/QWRTYUIOPSDFGHMJCKLZXVBN/qwrtyuiopsdfghmjcklzxvbn/
+    - xform/iu$/ǫ/
+    - xform/[iu]a$/ᴡ/
+    - xform/[uv]an$/ʀ/
+    - xform/[uv]e$/ᴛ/
+    - xform/ing$|uai$/ʏ/
+    - xform/^sh/ᴜ/
+    - xform/^ch/ɪ/
+    - xform/^zh/ᴠ/
+    - xform/uo$/ᴏ/
+    - xform/[uv]n$/ᴘ/
+    - xform/i?ong$/s/
+    - xform/[iu]ang$/ᴅ/
+    - xform/(.)en$/$1ғ/
+    - xform/(.)eng$/$1ɢ/
+    - xform/(.)ang$/$1ʜ/
+    - xform/ian$/ᴍ/
+    - xform/(.)an$/$1ᴊ/
+    - xform/iao$/ᴄ/
+    - xform/(.)ao$/$1ᴋ/
+    - xform/(.)ai$/$1ʟ/
+    - xform/(.)ei$/$1ᴢ/
+    - xform/ie$/x/
+    - xform/ui$/ᴠ/
+    - xform/(.)ou$/$1ʙ/
+    - xform/in$/ɴ/
+    - xlit/ǫᴡʀᴛʏᴜɪᴏᴘsᴅғɢʜᴍᴊᴄᴋʟᴢxᴠʙɴ/qwrtyuiopsdfghmjcklzxvbn/
    - abbrev/^(.).+$/$1/ # 首字母简拼
-    # 可输入大写字母。因为上面的双拼拼写规则用掉了大写字母。做了 xlit 转写，同时适配全拼和双拼。
-    - xlit/āḃçďēḟḡĥīĵḱĺḿńōṕɋŕśťūṽẃẋȳź/ABCDEFGHIJKLMNOPQRSTUVWXYZ/
--- a/double_pinyin_flypy.schema.yaml
+++ b/double_pinyin_flypy.schema.yaml
@ -10,7 +10,6 @@
 #
 # 默认启用的中英混输词库是全拼的，需要在 melt_eng.dict.yaml 中修改为对应的双拼的。

-
 # 方案说明
 schema:
  schema_id: double_pinyin_flypy
@ -237,32 +236,31 @@ speller:
    - derive/^([jqxy])u$/$1v/
    - derive/^([aoe])([ioun])$/$1$1$2/
    - xform/^([aoe])(ng)?$/$1$1$2/
-    - xform/iu$/Q/
-    - xform/(.)ei$/$1W/
-    - xform/uan$/R/
-    - xform/[uv]e$/T/
-    - xform/un$/Y/
-    - xform/^sh/U/
-    - xform/^ch/I/
-    - xform/^zh/V/
-    - xform/uo$/O/
-    - xform/ie$/P/
-    - xform/i?ong$/S/
-    - xform/ing$|uai$/K/
-    - xform/(.)ai$/$1D/
-    - xform/(.)en$/$1F/
-    - xform/(.)eng$/$1G/
-    - xform/[iu]ang$/L/
-    - xform/(.)ang$/$1H/
-    - xform/ian$/M/
-    - xform/(.)an$/$1J/
-    - xform/(.)ou$/$1Z/
-    - xform/[iu]a$/X/
-    - xform/iao$/N/
-    - xform/(.)ao$/$1C/
-    - xform/ui$/V/
-    - xform/in$/B/
-    - xlit/QWRTYUIOPSDFGHJKLZXCVBNM/qwrtyuiopsdfghjklzxcvbnm/
+    - xform/iu$/ǫ/
+    - xform/(.)ei$/$1ᴡ/
+    - xform/uan$/ʀ/
+    - xform/[uv]e$/ᴛ/
+    - xform/un$/ʏ/
+    - xform/^sh/ᴜ/
+    - xform/^ch/ɪ/
+    - xform/^zh/ᴠ/
+    - xform/uo$/ᴏ/
+    - xform/ie$/ᴘ/
+    - xform/i?ong$/s/
+    - xform/ing$|uai$/ᴋ/
+    - xform/(.)ai$/$1ᴅ/
+    - xform/(.)en$/$1ғ/
+    - xform/(.)eng$/$1ɢ/
+    - xform/[iu]ang$/ʟ/
+    - xform/(.)ang$/$1ʜ/
+    - xform/ian$/ᴍ/
+    - xform/(.)an$/$1ᴊ/
+    - xform/(.)ou$/$1ᴢ/
+    - xform/[iu]a$/x/
+    - xform/iao$/ɴ/
+    - xform/(.)ao$/$1ᴄ/
+    - xform/ui$/ᴠ/
+    - xform/in$/ʙ/
+    - xlit/ǫᴡʀᴛʏᴜɪᴏᴘsᴅғɢʜᴊᴋʟᴢxᴄᴠʙɴᴍ/qwrtyuiopsdfghjklzxcvbnm/
    - abbrev/^(.).+$/$1/  # 首字母简拼
-    # 可输入大写字母。因为上面的双拼拼写规则用掉了大写字母。做了 xlit 转写，同时适配全拼和双拼。
-    - xlit/āḃçďēḟḡĥīĵḱĺḿńōṕɋŕśťūṽẃẋȳź/ABCDEFGHIJKLMNOPQRSTUVWXYZ/
+  
--- a/double_pinyin_mspy.schema.yaml
+++ b/double_pinyin_mspy.schema.yaml
@ -241,34 +241,32 @@ speller:
    - derive/^([jqxy])u$/$1v/
    - derive/^([aoe].*)$/o$1/
    - xform/^([ae])(.*)$/$1$1$2/
-    - xform/iu$/Q/
-    - xform/[iu]a$/W/
-    - xform/er$|[uv]an$/R/
-    - xform/[uv]e$/T/
-    - xform/v$|uai$/Y/
-    - xform/^sh/U/
-    - xform/^ch/I/
-    - xform/^zh/V/
-    - xform/uo$/O/
-    - xform/[uv]n$/P/
-    - xform/i?ong$/S/
-    - xform/[iu]ang$/D/
-    - xform/(.)en$/$1F/
-    - xform/(.)eng$/$1G/
-    - xform/(.)ang$/$1H/
-    - xform/ian$/M/
-    - xform/(.)an$/$1J/
-    - xform/iao$/C/
-    - xform/(.)ao$/$1K/
-    - xform/(.)ai$/$1L/
-    - xform/(.)ei$/$1Z/
-    - xform/ie$/X/
-    - xform/ui$/V/
-    - derive/T$/V/
-    - xform/(.)ou$/$1B/
-    - xform/in$/N/
+    - xform/iu$/ǫ/
+    - xform/[iu]a$/ᴡ/
+    - xform/er$|[uv]an$/ʀ/
+    - xform/[uv]e$/ᴛ/
+    - xform/v$|uai$/ʏ/
+    - xform/^sh/ᴜ/
+    - xform/^ch/ɪ/
+    - xform/^zh/ᴠ/
+    - xform/uo$/ᴏ/
+    - xform/[uv]n$/ᴘ/
+    - xform/i?ong$/s/
+    - xform/[iu]ang$/ᴅ/
+    - xform/(.)en$/$1ғ/
+    - xform/(.)eng$/$1ɢ/
+    - xform/(.)ang$/$1ʜ/
+    - xform/ian$/ᴍ/
+    - xform/(.)an$/$1ᴊ/
+    - xform/iao$/ᴄ/
+    - xform/(.)ao$/$1ᴋ/
+    - xform/(.)ai$/$1ʟ/
+    - xform/(.)ei$/$1ᴢ/
+    - xform/ie$/x/
+    - xform/ui$/ᴠ/
+    - derive/T$/ᴠ/
+    - xform/(.)ou$/$1ʙ/
+    - xform/in$/ɴ/
    - xform/ing$/;/
-    - xlit/QWRTYUIOPSDFGHMJCKLZXVBN/qwrtyuiopsdfghmjcklzxvbn/
+    - xlit/ǫᴡʀᴛʏᴜɪᴏᴘsᴅғɢʜᴍᴊᴄᴋʟᴢxᴠʙɴ/qwrtyuiopsdfghmjcklzxvbn/
    - abbrev/^(.).+$/$1/  # 首字母简拼
-    # 可输入大写字母。因为上面的双拼拼写规则用掉了大写字母。做了 xlit 转写，同时适配全拼和双拼。
-    - xlit/āḃçďēḟḡĥīĵḱĺḿńōṕɋŕśťūṽẃẋȳź/ABCDEFGHIJKLMNOPQRSTUVWXYZ/
--- a/double_pinyin_ziguang.schema.yaml
+++ b/double_pinyin_ziguang.schema.yaml
@ -237,32 +237,30 @@ speller:
  algebra:
    - erase/^xx$/
    - derive/^([jqxy])u$/$1v/
-    - xform/^([aoe].*)$/O$1/  # 添上固定的零聲母o，先標記爲大寫O
-    - xform/en$/W/
-    - xform/eng$/T/
-    - xform/in$|uai$/Y/
-    - xform/^zh/U/
-    - xform/^sh/I/
-    - xform/uo$/O/
-    - xform/ai$/P/
-    - xform/^ch/A/
-    - xform/[iu]ang$/G/
-    - xform/ang$/S/  # ang should be placed after iang/uang
-    - xform/ie$/D/
-    - xform/ian$/F/
-    - xform/i?ong$/H/
-    - xform/er$|iu$/J/
-    - xform/ei$/K/
-    - xform/uan$/L/
+    - xform/^([aoe].*)$/ᴏ$1/  # 添上固定的零聲母o，先標記爲大寫O
+    - xform/en$/ᴡ/
+    - xform/eng$/ᴛ/
+    - xform/in$|uai$/ʏ/
+    - xform/^zh/ᴜ/
+    - xform/^sh/ɪ/
+    - xform/uo$/ᴏ/
+    - xform/ai$/ᴘ/
+    - xform/^ch/ᴀ/
+    - xform/[iu]ang$/ɢ/
+    - xform/ang$/s/  # ang should be placed after iang/uang
+    - xform/ie$/ᴅ/
+    - xform/ian$/ғ/
+    - xform/i?ong$/ʜ/
+    - xform/er$|iu$/ᴊ/
+    - xform/ei$/ᴋ/
+    - xform/uan$/ʟ/
    - xform/ing$/;/
-    - xform/ou$/Z/
-    - xform/[iu]a$/X/
-    - xform/iao$/B/
-    - xform/ue$|ui$|ve$/N/
-    - xform/un$/M/
-    - xform/ao$/Q/ # ao should be placed after iao
-    - xform/an$/R/ # an should be placed after uan/ian
-    - xlit/WTYUIOPAGSDFHJKLZXBNMQR/wtyuiopagsdfhjklzxbnmqr/
+    - xform/ou$/ᴢ/
+    - xform/[iu]a$/x/
+    - xform/iao$/ʙ/
+    - xform/ue$|ui$|ve$/ɴ/
+    - xform/un$/ᴍ/
+    - xform/ao$/ǫ/ # ao should be placed after iao
+    - xform/an$/ʀ/ # an should be placed after uan/ian
+    - xlit/ᴡᴛʏᴜɪᴏᴘᴀɢsᴅғʜᴊᴋʟᴢxʙɴᴍǫʀ/wtyuiopagsdfhjklzxbnmqr/
    - abbrev/^(.).+$/$1/ # 首字母简拼
-    # 可输入大写字母。因为上面的双拼拼写规则用掉了大写字母。做了 xlit 转写，同时适配全拼和双拼。
-    - xlit/āḃçďēḟḡĥīĵḱĺḿńōṕɋŕśťūṽẃẋȳź/ABCDEFGHIJKLMNOPQRSTUVWXYZ/
--- a/en_dicts/cn_en.dict.yaml
+++ b/en_dicts/cn_en.dict.yaml
@ -157,7 +157,6 @@ Beta版本	Betabanben
 AV女优	AVnvyou
 X战警	Xzhanjing
 YY语音	YYyuyin
-A4	Asi
 A4纸	Asizhi
 A4腰	Asiyao
 N多	Nduo
--- a/en_dicts/cn_en_double_pinyin.dict.yaml
+++ b/en_dicts/cn_en_double_pinyin.dict.yaml
@ -157,7 +157,6 @@ Beta版本	Betabjbf
 AV女优	AVnvyb
 X战警	Xvjjy
 YY语音	YYyuyn
-A4	Asi
 A4纸	Asivi
 A4腰	Asiyk
 N多	Ndo
--- a/en_dicts/cn_en_double_pinyin_abc.dict.yaml
+++ b/en_dicts/cn_en_double_pinyin_abc.dict.yaml
@ -157,7 +157,6 @@ Beta版本	Betabjbf
 AV女优	AVnvyb
 X战警	Xajjy
 YY语音	YYyuyc
-A4	Asi
 A4纸	Asiai
 A4腰	Asiyk
 N多	Ndo
--- a/en_dicts/cn_en_double_pinyin_flypy.dict.yaml
+++ b/en_dicts/cn_en_double_pinyin_flypy.dict.yaml
@ -157,7 +157,6 @@ Beta版本	Betabjbf
 AV女优	AVnvyz
 X战警	Xvjjk
 YY语音	YYyuyb
-A4	Asi
 A4纸	Asivi
 A4腰	Asiyc
 N多	Ndo
--- a/en_dicts/cn_en_double_pinyin_mspy.dict.yaml
+++ b/en_dicts/cn_en_double_pinyin_mspy.dict.yaml
@ -157,7 +157,6 @@ Beta版本	Betabjbf
 AV女优	AVnvyb
 X战警	Xvjj;
 YY语音	YYyuyn
-A4	Asi
 A4纸	Asivi
 A4腰	Asiyk
 N多	Ndo
--- a/en_dicts/cn_en_double_pinyin_ziguang.dict.yaml
+++ b/en_dicts/cn_en_double_pinyin_ziguang.dict.yaml
@ -157,7 +157,6 @@ Beta版本	Betabrbw
 AV女优	AVnvyz
 X战警	Xurj;
 YY语音	YYyuyy
-A4	Asi
 A4纸	Asiui
 A4腰	Asiyq
 N多	Ndo
--- a/en_dicts/en_ext.dict.yaml
+++ b/en_dicts/en_ext.dict.yaml
@ -1289,7 +1289,7 @@ New Technology File System	NTFS
 New Technology File System	NewTechnologyFileSystem
 Microsoft NTFS	NTFS
 Microsoft NTFS	MicrosoftNTFS
-chromeOS	chromeOS
+ChromeOS	ChromeOS
 GCD	GCD
 Grand Central Dispatch	GCD
 Grand Central Dispatch	GrandCentralDispatch
@ -2253,3 +2253,5 @@ Kubernetes	Kubernetes
 containerized	containerized
 shitty	shitty
 shitwork	shitwork
+A4	A4
+3D	3D
--- a/melt_eng.schema.yaml
+++ b/melt_eng.schema.yaml
@ -86,8 +86,6 @@ speller:
      - derive/[^a-zA-Z0-9]//
      # 禁用非英文、数字开头的编码
      - erase/^[\W|_].+$/
-      # 当开启自动调频时，保证大写+小写开头的词排在全大写的前面
-      # - derive/^([A-Z][A-Z]+)[a-z]+/$1/
      # 全小写
      - derive/^.+$/\L$0/
      # 全大写
--- a/rime_ice.schema.yaml
+++ b/rime_ice.schema.yaml
@ -263,9 +263,6 @@ speller:
    - derive/^([jqxy])u/$1v/
    - derive/^([jqxy])v/$1u/

-    ### 可输入大写字母，做了 xlit 转写是为了适配双拼
-    - xlit/āḃçďēḟḡĥīĵḱĺḿńōṕɋŕśťūṽẃẋȳź/ABCDEFGHIJKLMNOPQRSTUVWXYZ/
-
    ### 自动纠错
    # 有些规则对全拼简拼混输有副作用：如「x'ai 喜爱」被纠错为「xia 下」
    # zh、ch、sh