1 ;;; skkdic-utl.el --- Utility functions for handling SKK dictionary
3 ;; Copyright (C) 1995 Electrotechnical Laboratory, JAPAN.
4 ;; Licensed to the Free Software Foundation.
6 ;; Keywords: mule, multilingual, Japanese, SKK
8 ;; This file is part of GNU Emacs.
10 ;; GNU Emacs is free software; you can redistribute it and/or modify
11 ;; it under the terms of the GNU General Public License as published by
12 ;; the Free Software Foundation; either version 2, or (at your option)
15 ;; GNU Emacs is distributed in the hope that it will be useful,
16 ;; but WITHOUT ANY WARRANTY; without even the implied warranty of
17 ;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
18 ;; GNU General Public License for more details.
20 ;; You should have received a copy of the GNU General Public License
21 ;; along with GNU Emacs; see the file COPYING. If not, write to the
22 ;; Free Software Foundation, Inc., 59 Temple Place - Suite 330,
23 ;; Boston, MA 02111-1307, USA.
27 ;; SKK is a free Japanese input method running on Mule created by
28 ;; Masahiko Sato <masahiko@sato.riec.tohoku.ac.jp>. The Emacs Lisp
29 ;; library kkc.el provides a facility to convert a Japanese kana
30 ;; string to a kanji-kana-mixed string by using a SKK dictionary.
32 ;; This file provides a generic function to look up a SKK dictionary.
34 ;; The original SKK dictionary SKK-JISYO.L is converted to skkdic.el.
35 ;; We get entries of the dictionary in four variables (listed below)
36 ;; by loadig this file (or byte-compiled version skkdic.elc).
40 ;; The following four variables are set by loading skkdic.el[c].
41 (defvar skkdic-okuri-ari nil
42 "Nested alist for OKURI-ARI entries of SKK dictionary.")
44 (defvar skkdic-postfix nil
45 "Nested alist for SETSUBIJI (postfix) entries of SKK dictionary.")
47 (defvar skkdic-prefix nil
48 "Nested alist SETTOUJI (prefix) entries of SKK dictionary.")
50 (defvar skkdic-okuri-nasi nil
51 "Nested alist for OKURI-NASI entries of SKK dictionary.")
53 (defconst skkdic-okurigana-table
54 '((?
\e$B$!
\e(B . ?a) (?
\e$B$"
\e(B . ?a) (?
\e$B$#
\e(B . ?i) (?
\e$B$$
\e(B . ?i) (?
\e$B$%
\e(B . ?u)
55 (?
\e$B$&
\e(B . ?u) (?
\e$B$'
\e(B . ?e) (?
\e$B$(
\e(B . ?e) (?
\e$B$)
\e(B . ?o) (?
\e$B$*
\e(B . ?o)
56 (?
\e$B$+
\e(B . ?k) (?
\e$B$,
\e(B . ?g) (?
\e$B$-
\e(B . ?k) (?
\e$B$.
\e(B . ?g) (?
\e$B$/
\e(B . ?k)
57 (?
\e$B$0
\e(B . ?g) (?
\e$B$1
\e(B . ?k) (?
\e$B$2
\e(B . ?g) (?
\e$B$3
\e(B . ?k) (?
\e$B$4
\e(B . ?g)
58 (?
\e$B$5
\e(B . ?s) (?
\e$B$6
\e(B . ?z) (?
\e$B$7
\e(B . ?s) (?
\e$B$8
\e(B . ?j) (?
\e$B$9
\e(B . ?s)
59 (?
\e$B$:
\e(B . ?z) (?
\e$B$;
\e(B . ?s) (?
\e$B$<
\e(B . ?z) (?
\e$B$=
\e(B . ?s) (?
\e$B$>
\e(B . ?z)
60 (?
\e$B$?
\e(B . ?t) (?
\e$B$@
\e(B . ?d) (?
\e$B$A
\e(B . ?t) (?
\e$B$B
\e(B . ?d) (?
\e$B$C
\e(B . ?t)
61 (?
\e$B$D
\e(B . ?t) (?
\e$B$E
\e(B . ?d) (?
\e$B$F
\e(B . ?t) (?
\e$B$G
\e(B . ?d) (?
\e$B$H
\e(B . ?t) (?
\e$B$I
\e(B . ?d)
62 (?
\e$B$J
\e(B . ?n) (?
\e$B$K
\e(B . ?n) (?
\e$B$L
\e(B . ?n) (?
\e$B$M
\e(B . ?n) (?
\e$B$N
\e(B . ?n)
63 (?
\e$B$O
\e(B . ?h) (?
\e$B$P
\e(B . ?b) (?
\e$B$Q
\e(B . ?p) (?
\e$B$R
\e(B . ?h) (?
\e$B$S
\e(B . ?b)
64 (?
\e$B$T
\e(B . ?p) (?
\e$B$U
\e(B . ?h) (?
\e$B$V
\e(B . ?b) (?
\e$B$W
\e(B . ?p) (?
\e$B$X
\e(B . ?h)
65 (?
\e$B$Y
\e(B . ?b) (?
\e$B$Z
\e(B . ?p) (?
\e$B$[
\e(B . ?h) (?
\e$B$\
\e(B . ?b) (?
\e$B$]
\e(B . ?p)
66 (?
\e$B$^
\e(B . ?m) (?
\e$B$_
\e(B . ?m) (?
\e$B$`
\e(B . ?m) (?
\e$B$a
\e(B . ?m) (?
\e$B$b
\e(B . ?m)
67 (?
\e$B$c
\e(B . ?y) (?
\e$B$d
\e(B . ?y) (?
\e$B$e
\e(B . ?y) (?
\e$B$f
\e(B . ?y) (?
\e$B$g
\e(B . ?y) (?
\e$B$h
\e(B . ?y)
68 (?
\e$B$i
\e(B . ?r) (?
\e$B$j
\e(B . ?r) (?
\e$B$k
\e(B . ?r) (?
\e$B$l
\e(B . ?r) (?
\e$B$m
\e(B . ?r)
69 (?
\e$B$o
\e(B . ?w) (?
\e$B$p
\e(B . ?w) (?
\e$B$q
\e(B . ?w) (?
\e$B$r
\e(B . ?w)
72 "Alist of Okuriganas vs trailing ASCII letters in OKURI-ARI entry.")
74 (defun skkdic-merge-head-and-tail (heads tails postfix)
79 (>= (length (car heads)) min-len))
83 (>= (length (car tail)) min-len))
84 (setq l (cons (concat (car heads) (car tail)) l)))
85 (setq tail (cdr tail)))))
86 (setq heads (cdr heads)))
89 (defconst skkdic-jisx0208-hiragana-block (nth 1 (split-char ?
\e$B$"
\e(B)))
91 (defun skkdic-lookup-key (seq len &optional postfix prefer-noun)
92 "Return a list of conversion string for sequence SEQ of length LEN.
94 SEQ is a vector of Kana characters to be converted by SKK dictionary.
95 If LEN is shorter than the length of KEYSEQ, the first LEN keys in SEQ
96 are took into account.
98 Optional 3rd arg POSTFIX non-nil means SETSUBIJI (postfix) are also
99 considered to find conversion strings.
101 Optional 4th arg PREFER-NOUN non-nil means that the conversions
102 without okurigana are placed at the head of the returned list."
103 (or skkdic-okuri-nasi
105 (load-library "skk/skkdic")
107 (with-output-to-temp-buffer "*Help*"
108 (princ "The library `skkdic' can't be loaded.
110 The most common case is that you have not yet installed the library
111 included in LEIM (Libraries of Emacs Input Method) which is
112 distributed separately from Emacs.
114 LEIM is available from the same ftp directory as Emacs."))
115 (signal (car err) (cdr err)))))
117 (let ((vec (make-vector len 0))
120 ;; At first, generate vector VEC from SEQ for looking up SKK
121 ;; alists. Nth element in VEC corresponds to Nth element in SEQ.
122 ;; The values are decided as follows.
123 ;; If SEQ[N] is `
\e$B!<
\e(B', VEC[N] is 0,
124 ;; else if SEQ[N] is a Hiragana character, VEC[N] is:
125 ;; ((The 2nd position code of SEQ[N]) - 32),
126 ;; else VEC[N] is 128.
128 (let ((ch (aref seq i))
130 (if (= ch ?
\e$B!<
\e(B)
132 (setq elts (split-char ch))
133 (if (and (eq (car elts) 'japanese-jisx0208)
134 (= (nth 1 elts) skkdic-jisx0208-hiragana-block))
135 (aset vec i (- (nth 2 elts) 32))
139 ;; Search OKURI-NASI entries.
140 (setq entry (lookup-nested-alist vec skkdic-okuri-nasi len 0 t))
141 (if (consp (car entry))
142 (setq entry (copy-sequence (car entry)))
146 ;; Search OKURI-NASI entries with postfixes.
147 (let ((break (max (- len (car skkdic-postfix)) 1))
148 entry-head entry-postfix entry2)
150 (if (and (setq entry-head
151 (lookup-nested-alist vec skkdic-okuri-nasi
153 (consp (car entry-head))
155 (lookup-nested-alist vec skkdic-postfix
157 (consp (car entry-postfix))
158 (setq entry2 (skkdic-merge-head-and-tail
159 (car entry-head) (car entry-postfix) t)))
162 (setq entry entry2)))
163 (setq break (1+ break)))))
165 ;; Search OKURI-NASI entries with prefixes.
166 (let ((break (min (car skkdic-prefix) (- len 2)))
167 entry-prefix entry-tail entry2)
169 (if (and (setq entry-prefix
170 (lookup-nested-alist vec skkdic-prefix break 0 t))
171 (consp (car entry-prefix))
173 (lookup-nested-alist vec skkdic-okuri-nasi len break t))
174 (consp (car entry-tail))
175 (setq entry2 (skkdic-merge-head-and-tail
176 (car entry-prefix) (car entry-tail) nil)))
180 (setq entry entry2))))
181 (setq break (1- break))))
183 ;; Search OKURI-ARI entries.
184 (let ((okurigana (assq (aref seq (1- len)) skkdic-okurigana-table))
188 (setq orig-element (aref vec (1- len)))
189 (aset vec (1- len) (- (cdr okurigana)))
190 (if (and (setq entry2 (lookup-nested-alist vec skkdic-okuri-ari
192 (consp (car entry2)))
194 (setq entry2 (copy-sequence (car entry2)))
196 (okuri (char-to-string (aref seq (1- len)))))
198 (setcar l (concat (car l) okuri))
203 (setq entry2 (nreverse entry2))
206 (setq entry (nreverse entry2))))))
207 (aset vec (1- len) orig-element))))
212 (provide 'skkdic-utl)
214 ;; skkdic-utl.el ends here