-
Notifications
You must be signed in to change notification settings - Fork 6
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
Showing
194 changed files
with
6,279,253 additions
and
774,697 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,46 @@ | ||
# Rime dict | ||
# encoding: utf-8 | ||
#〔你還可以在這註釋字典來源、變動記錄等〕 | ||
name: "cangjie6.extended" #引用的字典名,確保與文件名相一致 | ||
version: "0.1" #請確保每次改動陞版本號 | ||
sort: by_weight #字典初始排序,可選original或by_weight | ||
use_preset_vocabulary: false #是否引入「八股文」〔含字詞頻、詞庫〕 | ||
# max_phrase_length: 配合use_preset_vocabulary:,設定導入詞條最大詞長 | ||
# min_phrase_weight: 配合use_preset_vocabulary:,設定導入詞條最小詞頻 | ||
|
||
import_tables: #加載其它外部碼表 | ||
- cangjie6 #單字碼表由cangjie6.dict.yaml導入 | ||
columns: #此字典爲純詞典,無單字編碼,僅有字和詞頻 以Tab分隔各列,各列依columns:定義排列。 | ||
- text #第一列:字/詞【文本】 | ||
- code #第二列:code【碼】 | ||
- weight #第三列:字/詞頻【權重】 | ||
- stem #第四列:【造詞碼】 | ||
encoder: #形碼造詞規則 | ||
exclude_patterns: #取消某編碼的造詞資格 | ||
- '^z.*$' | ||
rules: #可用length_equal:和length_in_range:定義。大寫字母表示字序,小寫字母表示其所跟隨的大寫字母所以表的字中的編碼序 | ||
- length_equal: 2 #對於二字詞 | ||
formula: "AaAzBaBbBz" #取第一字首尾碼、第二字首次尾碼 | ||
- length_equal: 3 #對於三字詞 | ||
formula: "AaAzBaYzZz" #取第一字首尾碼、第二字首尾碼、第三字尾碼 | ||
- length_in_range: [4, 5] #對於四至五字詞 | ||
formula: "AaBzCaYzZz" #取第一字首碼,第二字尾碼、第三字首碼、倒數第二字尾碼、最後一字尾碼 | ||
tail_anchor: "'" #造詞碼包含結構分割符〔僅用於倉頡〕 | ||
|
||
|
||
# cangjie6.dict.yaml | ||
... | ||
個 owjr 246268 ow'jr | ||
看 hqbu 245668 | ||
中 l 243881 | ||
呢 rsp 242970 | ||
來 doo 235101 | ||
嗎 rsqf 221092 | ||
爲 bhnf 211340 | ||
會 owfa 209844 | ||
她 vpd 204725 | ||
與 xyc 203975 | ||
給 vfor 193007 | ||
等 hgdi 183340 | ||
這 yymr 181787 | ||
用 bq 168934 b'q |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Oops, something went wrong.