xfnw
/
plan9fox
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Merge branch 'front' of git://git.9front.org/plan9front/plan9front into front

This commit is contained in:
xfnw 2022-07-07 13:37:09 -04:00
parent 4223c2a326 566c512106
commit 33ba68d23d
11 changed files with 11559 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7586
lib/kanji.jisho Normal file
View File

File diff suppressed because it is too large Load Diff

106
sys/man/1/ktrans Normal file
View File

@ -0,0 +1,106 @@
.TH KTRANS 1
.SH NAME
ktrans \- language transliterator
.SH SYNOPSIS
.B ktrans
.SH DESCRIPTION
The
.I ktrans
program works with
.IR kbdfs (8)
to transliterate typed letter sequences into characters for languages
that do not use the Latin character set, and pipes the result to
.BR /dev/cons .
The language is selected by typing a control character:
.TP
.B ctl-t
return to default English mode (no transliteration).
.TP
.B ctl-n
Japanese hiragana: interpret lower-case letters as a Hepburn
representation of hiragana. In this mode, typing ctl-\\ looks up the
last `word' in a hiragana-kanji dictionary and replaces it.
Subsequent ctl-\\ characters cycle through the possibilities. A word
is the longest immediately preceding unbroken string of hiragana
characters.
.TP
.B ctl-k
Japanese katakana.
.TP
.B ctl-l
If you want to put the hiragana not converted, you can type.
.TP
.B ctl-x
Read kana-kanji conversion dictionary once more, and renews it. This
will be convenient when you updated kana-kanji conversion dictionary
on such acme editor.In default, the kana-kanji conversion dictionary
is read once at beginning and to make a hashed table, which will be
arranged so that the last selected candidate will be the first
candidate for later search.
.TP
.B ctl-r
Russian: interpret letters as Cyrillic; the transliteration is mostly
phonetic, with
.B '
for
.IR myagkij-znak
(ь),
.B ''
for
.I tverdyj-znak
(ъ)
.I yo
for ё,
.B j
for
.IR i-kratkaya
(й).
.TP
.B ctl-o
Greek.
.TP
.B ctl-s
Korean.
.PP
To use it you have to run it before a rio session. You can put it on your $home/lib/profile like:
.EX
...
ktrans
rio -i riostart
...
.EE
or run it with a sub-rio on a window like:
.EX
% @{ktrans; rio}
.EE
.PP
.SH SOURCE
.B /sys/src/cmd/ktrans
.SH SEE ALSO
.IR rio (1)
.IR kbdfs (8)
.br
.IR /sys/src/cmd/ktrans/README.kenji
.br
.IR /sys/src/cmd/ktrans/READMEJ.kenji
.SH EXAMPLES
If you want to make the Japanese text as below:
私は毎日35分以上歩いて、 更に10分電車に乗って学校に通います。
健康の維持にも役だっていますが、 なかなかたのしいものです。
your keyboard typing stream should be:
[^l]watashiHA[^\\]mainichi[^\\]35[^l]fun[^\\]ijou[^\\]aruIte,
[^\\]saraNI[^\\]10[^l]fun[^\\]denshaNI[^\\]noTte[^\\]gakkouNI
[^\\]kayoImasu.[^\\]kenkouNO[^\\]ijiNImo[^\\]yakuDAtteimasuga,
[^\\]nakanakatanoshiImonodesu.
where [^\\] and [^l] indicate 'ctl-\\' and 'ctl-l',
respectively. See README.kenji for the details of this Japanese input
method.
.SH BUGS
.PP
There is no way to generate the control characters literally. At the
beggining of a new line, you have to begin with ctl-l for successful
kana-kanji conversion.

10
sys/src/9/imx8/ccm.c
View File

@ -822,31 +822,31 @@ static Clock clocks[] = {
{ "sai2.ipg_clk_s", AUDIO_IPG_CLK_ROOT, 52 },
{ "sai2.ipg_clk_sai_mclk_1", SAI2_CLK_ROOT, 52 },
{ "sai2.ipt_clk_sai_bclk", SAI2_CLK_ROOT, 52 },
{ "sai2.ipt_clk_sai_bclk_b", SAI1_CLK_ROOT, 52 },
{ "sai2.ipt_clk_sai_bclk_b", SAI2_CLK_ROOT, 52 },
{ "sai3.ipg_clk", AUDIO_IPG_CLK_ROOT, 53 },
{ "sai3.ipg_clk_s", AUDIO_IPG_CLK_ROOT, 53 },
{ "sai3.ipg_clk_sai_mclk_1", SAI3_CLK_ROOT, 53 },
{ "sai3.ipt_clk_sai_bclk", SAI3_CLK_ROOT, 53 },
{ "sai3.ipt_clk_sai_bclk_b", SAI1_CLK_ROOT, 53 },
{ "sai3.ipt_clk_sai_bclk_b", SAI3_CLK_ROOT, 53 },
{ "sai4.ipg_clk", AUDIO_IPG_CLK_ROOT, 54 },
{ "sai4.ipg_clk_s", AUDIO_IPG_CLK_ROOT, 54 },
{ "sai4.ipg_clk_sai_mclk_1", SAI4_CLK_ROOT, 54 },
{ "sai4.ipt_clk_sai_bclk", SAI4_CLK_ROOT, 54 },
{ "sai4.ipt_clk_sai_bclk_b", SAI1_CLK_ROOT, 54 },
{ "sai4.ipt_clk_sai_bclk_b", SAI4_CLK_ROOT, 54 },
{ "sai5.ipg_clk", AUDIO_IPG_CLK_ROOT, 55 },
{ "sai5.ipg_clk_s", AUDIO_IPG_CLK_ROOT, 55 },
{ "sai5.ipg_clk_sai_mclk_1", SAI5_CLK_ROOT, 55 },
{ "sai5.ipt_clk_sai_bclk", SAI5_CLK_ROOT, 55 },
{ "sai5.ipt_clk_sai_bclk_b", SAI1_CLK_ROOT, 55 },
{ "sai5.ipt_clk_sai_bclk_b", SAI5_CLK_ROOT, 55 },
{ "sai6.ipg_clk", AUDIO_IPG_CLK_ROOT, 56 },
{ "sai6.ipg_clk_s", AUDIO_IPG_CLK_ROOT, 56 },
{ "sai6.ipg_clk_sai_mclk_1", SAI6_CLK_ROOT, 56 },
{ "sai6.ipt_clk_sai_bclk", SAI6_CLK_ROOT, 56 },
{ "sai6.ipt_clk_sai_bclk_b", SAI1_CLK_ROOT, 56 },
{ "sai6.ipt_clk_sai_bclk_b", SAI6_CLK_ROOT, 56 },
{ "sctr.ipg_clk", IPG_CLK_ROOT, 57 },
{ "sctr.ipg_clk_s", IPG_CLK_ROOT, 57 },

30
sys/src/9/imx8/pciimx.c
View File

@ -410,6 +410,34 @@ pcicfginit(void)
rootinit(&ctlrs[1]);
}
/* undocumented magic to avoid interference between lcdif and pcie */
static void
qosmagic(void)
{
static u32int *qosc = (u32int*)(VIRTIO + 0x7f0000);
/* unlock */
qosc[0x0000/4] = 0x0;
qosc[0x0000/4] = 0x1;
qosc[0x0060/4] = 0x0;
/* pci1 */
qosc[0x1000/4] = 0x0;
qosc[0x1000/4] = 0x1;
qosc[0x1050/4] = 0x01010100;
qosc[0x1060/4] = 0x01010100;
qosc[0x1070/4] = 0x01010100;
qosc[0x1000/4] = 0x1;
/* pcie2 */
qosc[0x2000/4] = 0x0;
qosc[0x2000/4] = 0x1;
qosc[0x2050/4] = 0x01010100;
qosc[0x2060/4] = 0x01010100;
qosc[0x2070/4] = 0x01010100;
qosc[0x2000/4] = 0x1;
}
enum {
SRC_PCIEPHY_RCR = 0x2C/4,
SRC_PCIE2_RCR = 0x48/4,
@ -494,4 +522,6 @@ pciimxlink(void)
resetc[SRC_PCIE2_RCR] &= ~(PCIE_BTN | PCIE_G_RST);
pcicfginit();
qosmagic();
}

108
sys/src/cmd/ktrans/README.kenji Normal file
View File

@ -0,0 +1,108 @@
This version of ktrans works with pipefile by Rob Pike, which replaces /dev/kbd of
2nd Edition Plan 9 by Dennis Ritchie. By this new idea, we can input Japanese
anytime onto any windows. I included his post to 9fans mailing-list here (pipefile
file).
This is a distribution as a derived work license of Plan 9, and I included the
Plan 9 License term here. Please refer to it on the details of this license.
Main features are as follows:
1) There is a "local" dictionary file for translation from kana to kanji, which can
easily be edited by the user. The default file name is $home/lib/ktrans-jisho.
If you want to use another dictionary file, set the KTJISHO environment
variable to point to that file. This dictionary comprises many lines of
edittable text strings.
2) Capital romaji input is used for words such as verbs or adjectives with okurigana,
which follows the idea of the SKK system by Masahiko Sato of Kyoto Univ.
(masahiko@kuis.kyoto-u.ac.jp). If you want to get the kanji string (runes)
"動かす", which is a verb, you may input "ugoKasu" from the keyboard.
Note here the Kasu's k is a capital (important). You will see hiragana
runes "うごかす", and then the kanji runes of "動かす", when you type
"Shift+Space".
If you are satisfied by that translation, continue to input the next word.
If you are not pleased with that candidate, hit 'Shift+Space' once more
to see more candiates for that hiragana input. When there are no more candidates
registered in your dictionary, you will see the initial hiragana input.
3) For Japanese "joshi", a post-positioned short word after a noun, you can use another
method that I developed for this work. If you want the kanji string (runes) "私は",
then type "watashiHA" from the keyboard. Note that the sound of "wa(ha)" is expressed
as capitalized "HA". You will see a hiragana string of "わたしは", and then "私は"
after `Shift+Space'.
4) A control sequence of 'ctl-l' is introduced to leave input hiragana runes unchanged.
This is occasionally neccessary.
5) A simple leaning mechanism has been implemented for the in-memory hashing
dictinary, in which the most recently used kanji runes (candidate) moves to the top
of the list of candidates. This is valid only during the session you called ktrans.
It is done this way intentionally, because the present learning method is ..well...
naive. ^_^ I know this; however, I believe you can solve it by making a good
dictionary best fitted to your purposes on your own.
6) 'ctl-x' re-reads the new kana-kanji translation dictionary when you have edited your
kana-kanji translation, and want to incorporate it into your current in-memory translation
dictionary. The kana-kanji translation dictionary is usually read only once, at the
beginning of the ktrans session. I believe this simplification is not a serious constraint,
because you can edit the dictionary anytime by co-working with acme and using this ctl-x
mechanism.
7) A mode change to kana-input is triggered by 'ctl-n', ctl-k for katakana mode,
ctl-g for Greek mode, and ctl-r for Russian mode.
8) As the starting $home/lib/ktrans-jisho, you may re-format the SKK-JISYO.S (66.9KB) of the
SKK system, which can be retrieved from ftp.kuis.kyoto-u.ac.jp. The next three lines
show the short sed filter to transform from an SKK type dictionary to Plan 9. Before
this, you should change the kanji code of the SKK dictionary from ujis(euc) to UTF-8 by
the tcs utility, of course.
s/\// /g
s/ / /g
s/ $//g
The header items are sorted in a strange order in the original SKK dictionary.
This implementation does not care about the order, therefore, you can change it on
your own.
9) SKK jisho, such as SKK-JISYO.S, is composed of two parts, okuri-ari and okuri-nashi
entries. This greatly depends on the Japanese grammer, and okuri-ari may represent
verb/adjective etc., i.e., not noun. These two parts work differently in the original
SKK system, however, I did not employ that method; rather, I took a simple approarch
as described in (2) and (3). Here, we make no difference between these two parts,
and the reason why I left the two-part structure is just to make it easier to read for
editting. Of course, you can change it without any side-effects.
10) The essence of this Japanese input method is to convert every one word by one key
triggering. This may cause some cumbersome feelings for Nihongo users who are accustomed
to, say, Windows. I know this. However, I intended to keep the codes as compact as
possible as a first step towards developing a Nihongo input system on Plan 9.
Furthermore, I've never seen the latter work perfectly. I think the conversion failed
essentially when we see more than, say, five/six candidates for one set of hiragana runes.
Finaly, I'd like to add that I have no problem to write long Japanese documents by
this version.
11) The translation trigger key has been changed from ^t to Shift+Space, because
we experienced butting of the trigger key sequence sometime. For this reason,
you have to edit the key-binding table, such as kbtabshift[0x39] in /sys/src/9/pc/kbd.c
or keymapshift[0x79] in /sys/src/9/ss/screen.c to assign Shift+Space to '^\'.
I use here '^\' as the trigger key. Therefore, you can trigger translation
from kana to kanji by Shit+Space or just '^\'.
12) A usage example: If you want to make the Japanese text as below:
私は毎日35分以上歩いて、 更に10分電車に乗って学校に通います。
健康の維持にも役だっていますが、 なかなかたのしいものです。
your keyboard typing stream should be:
watashiHA[^t]mainichi[^t]35[^l]fun[^t]ijou[^t]aruIte, [^t]saraNI[^t]
10[^l]fun[^t]denshaNI[^t]noTte[^t]gakkouNI[^t]kayoImasu.[^t]
kenkouNO[^t]ijiNImo[^t]yakuDAtteimasuga, [^t]nakanaka[^l]tanoshiI[^t]
monodesu.[^l]
where [^t], [^l] indicates 'Shift+Space' and 'ctl-l', respectively.
Kenji Okamoto August 14, 2000

126
sys/src/cmd/ktrans/READMEJ.kenji Normal file
View File

@ -0,0 +1,126 @@
Plan 9がRelase 3になってソースが公開されました。このため、更に多くのユーザがPlan 9を
使い始める事になると思います。このバージョンになって、Windowシステムが8½からrioに
変更になり、それにともなって、release 2に含まれていたktransが無くなりました。
そこで、Rob Pikeさんにお願いしたら、pipefileというすばらしいアイデアを考えて戴け
ました。これはrelease 2でDennis Ritchieさんが提供した/dev/kbdを置き替えるもので、
このいきさつは、Pikeさんの9fansのlmailing-listへの投稿を同封してありますので、
そちら(pipefile)を御覧下さい。この方法は何時でもどのウィンドへも日本語を入力出来る
ので、以前のバージョンの様にウィンド毎にktransを起動する必要がなくなりました。
pipefileはrioより前に起動される必要がありますので、ここに同封したKanjiという
スクリプトを各自のlib/profileにrioを起動する替わりに、このKanjiスクリプトを
起動する様にして下さい。
Main features are as follows:
1) There is a "local" dictionary file for translation from kana to kanji, which can
easily be edited by the user. The default file name is $home/lib/ktrans-jisho.
If you want to use another dictionary file, set the KTJISHO environment
variable to point to that file. This dictionary comprises many lines of
edittable text strings.
2) Capital romaji input is used for words such as verbs or adjectives with okurigana,
which follows the idea of the SKK system by Masahiko Sato of Kyoto Univ.
(masahiko@kuis.kyoto-u.ac.jp). If you want to get the kanji string (runes)
"動かす", which is a verb, you may input "ugoKasu" from the keyboard.
Note here the Kasu's k is a capital (important). You will see hiragana
runes "うごかす", and then the kanji runes of "動かす", when you type
"Shift+Space".
If you are satisfied by that translation, continue to input the next word.
If you are not pleased with that candidate, hit 'Shift+Space' once more
to see more candiates for that hiragana input. When there are no more candidates
registered in your dictionary, you will see the initial hiragana input.
3) For Japanese "joshi", a post-positioned short word after a noun, you can use another
method that I developed for this work. If you want the kanji string (runes) "私は",
then type "watashiHA" from the keyboard. Note that the sound of "wa(ha)" is expressed
as capitalized "HA". You will see a hiragana string of "わたしは", and then "私は"
after `Shift+Space'.
4) A control sequence of 'ctl-l' is introduced to leave input hiragana runes unchanged.
This is occasionally neccessary.
5) A simple leaning mechanism has been implemented for the in-memory hashing
dictinary, in which the most recently used kanji runes (candidate) moves to the top
of the list of candidates. This is valid only during the session you called ktrans.
It is done this way intentionally, because the present learning method is ..well...
naive. ^_^ I know this; however, I believe you can solve it by making a good
dictionary best fitted to your purposes on your own.
6) 'ctl-x' re-reads the new kana-kanji translation dictionary when you have edited your
kana-kanji translation, and want to incorporate it into your current in-memory translation
dictionary. The kana-kanji translation dictionary is usually read only once, at the
beginning of the ktrans session. I believe this simplification is not a serious constraint,
because you can edit the dictionary anytime by co-working with acme and using this ctl-x
mechanism.
7) A mode change to kana-input is triggered by 'ctl-n', ctl-k for katakana mode,
ctl-g for Greek mode, and ctl-r for Russian mode.
8) As the starting $home/lib/ktrans-jisho, you may re-format the SKK-JISYO.S (66.9KB) of the
SKK system, which can be retrieved from ftp.kuis.kyoto-u.ac.jp. The next three lines
show the short sed filter to transform from an SKK type dictionary to Plan 9. Before
this, you should change the kanji code of the SKK dictionary from ujis(euc) to UTF-8 by
the tcs utility, of course.
s/\// /g
s/ / /g
s/ $//g
The header items are sorted in a strange order in the original SKK dictionary.
This implementation does not care about the order, therefore, you can change it on
your own.
9) SKK jisho, such as SKK-JISYO.S, is composed of two parts, okuri-ari and okuri-nashi
entries. This greatly depends on the Japanese grammer, and okuri-ari may represent
verb/adjective etc., i.e., not noun. These two parts work differently in the original
SKK system, however, I did not employ that method; rather, I took a simple approarch
as described in (2) and (3). Here, we make no difference between these two parts,
and the reason why I left the two-part structure is just to make it easier to read for
editting. Of course, you can change it without any side-effects.
10) The essence of this Japanese input method is to convert every one word by one key
triggering. This may cause some cumbersome feelings for Nihongo users who are accustomed
to, say, Windows. I know this. However, I intended to keep the codes as compact as
possible as a first step towards developing a Nihongo input system on Plan 9.
Furthermore, I've never seen the latter work perfectly. I think the conversion failed
essentially when we see more than, say, five/six candidates for one set of hiragana runes.
Finaly, I'd like to add that I have no problem to write long Japanese documents by
this version.
11) The translation trigger key has been changed from ^t to Shift+Space, because
we experienced butting of the trigger key sequence sometime. For this reason,
you have to edit the key-binding table, such as kbtabshift[0x39] in /sys/src/9/pc/kbd.c
or keymapshift[0x79] in /sys/src/9/ss/screen.c to assign Shift+Space to '^\'.
I use here '^\' as the trigger key. Therefore, you can trigger translation
from kana to kanji by Shit+Space or just '^\'.
12) A usage example: If you want to make the Japanese text as below:
私は毎日35分以上歩いて、 更に10分電車に乗って学校に通います。
健康の維持にも役だっていますが、 なかなかたのしいものです。
your keyboard typing stream should be:
watashiHA[^t]mainichi[^t]35[^l]fun[^t]ijou[^t]aruIte, [^t]saraNI[^t]
10[^l]fun[^t]denshaNI[^t]noTte[^t]gakkouNI[^t]kayoImasu.[^t]
kenkouNO[^t]ijiNImo[^t]yakuDAtteimasuga, [^t]nakanaka[^l]tanoshiI[^t]
monodesu.[^l]
where [^t], [^l] indicates 'Shift+Space' and 'ctl-l', respectively.
Kenji Okamoto August 14, 2000
これはRelease 2のPlan 9に含まれていたDennis Ritchieさんのktransを機能強化したもので、
大阪府立大学の岡本健二が作成いたしました。 疑問、提案等がございましたら、
okamoto@granite.cias.osakafu-u.ac.jpまで御連絡ください。
なお, Plan 9そのものにつきましては、
http://basalt.cias.osakafu-u.ac.jp/plan9/p9index.html に95年度より
ささやかなWeb Pageをもっていますので、そちらも参照くださいませ。
なおこのプログラムはPlan 9のderived workとしてのライセンスを持った配布となります。
Plan 9のLicense fileを同封してありますので、ここに書かれている事を守ってお使い
下さいませ。
大阪府立大学総合科学部 岡本健二 August 14, 2000

211
sys/src/cmd/ktrans/jisho.c Normal file
View File

@ -0,0 +1,211 @@
/*
* open jisho file, and set the size of this jisho etc
*
* Kenji Okamoto August 4, 2000
* Osaka Prefecture Univ.
* okamoto@granite.cias.osakafu-u.ac.jp
*/
#include <u.h>
#include <libc.h>
#include <bio.h>
#include "jisho.h"
Dictionary *openQDIC(char *);
void freeQDIC(Dictionary*);
KouhoList *getKouhoHash(Dictionary*, char *);
KouhoList *getKouhoFile(DicList*, char *);
void selectKouho(KouhoList **, KouhoList*);
int hashVal(char *);
void addHash(Hash **, DicList*);
/*
* Open QuickDIC (hashed personal dictionary)
* open skk styled ktrans dictionary file, and make its hash table
* based on individual header kana strings
*
* KouhoList
* |---------|
* Hash |---->kouho---->kouhotop
* |-------| |
* dic---->dhash---->dicindex---->kanahead
* |--------| |--------|
* Dictionary DicList
*
*/
Dictionary *
openQDIC(char *dicname)
{
Biobuf *f;
void *Bbuf;
Dictionary *dic;
DicList *dicitem; /* for a future extension */
char buf[1024], *startstr, *endstr;
int i;
SET(dicitem); /* yes, I know I'm wrong, but... */
dic = (Dictionary*)malloc(sizeof(Dictionary));
/* make room for pointer array (size=HASHSIZE) of hash table */
for(i=0; i< HASHSIZE; i++) dic->dhash[i] = 0;
dic->dlist = 0; /* for a future extension (more than one dics ^_^ */
if ((f = Bopen(dicname, OREAD)) == 0)
return dic;
/* make hash table by the dic's header word */
while(Bbuf = Brdline(f, '\n')) {
strncpy(buf, (char *)Bbuf, Blinelen(f));
if (buf[0] == ';') /* comment line */
continue;
else {
/* get header word from jisho */
startstr = buf;
if(!(endstr = utfutf(startstr, "\t"))) break;
*endstr = '\0';
/* dicitem includes each header word from the jisho */
dicitem = (DicList*)malloc(sizeof(DicList)+(endstr-startstr+1));
dicitem->nextitem = 0; /* for a future extension */
strcpy(dicitem->kanahead, startstr);
dicitem->kouho = getKouhoFile(dicitem, endstr); /* read kouho from jisho */
addHash(dic->dhash, dicitem);
}
continue;
}
dic->dlist = dicitem;
Bterm(f);
return dic;
}
/*
* free dynamically allocated memory
*/
void
freeQDIC(Dictionary *dic)
{
Hash *hash1, *hash2;
DicList *dlist, *dlist2;
int l;
for (dlist = dic->dlist;
dlist != 0;
dlist2 = dlist, dlist = dlist->nextitem, free((void *)dlist2));
for (l = 0; l < HASHSIZE; l++) {
for (hash1 = dic->dhash[l]; hash1; hash1 = hash2) {
if (hash1->next !=0) {
hash2 = hash1->next;
free((void *)hash1);
}else
break;
}
}
free((void *)dic);
}
int
hashVal(char *s)
{
uint h;
h = 0x811c9dc5;
while(*s != 0)
h = (h^(uchar)*s++) * 0x1000193;
return h % HASHSIZE;
}
void
addHash(Hash **hash, DicList *ditem)
{
Hash *h;
int v;
v = hashVal(ditem->kanahead);
h = (Hash*)malloc(sizeof(Hash));
h->dicindex = ditem;
h->length = strlen(ditem->kanahead);
h->next = hash[v];
hash[v] = h;
}
/*
* read Kouho list from the jisho file defined by Biobuf descriptor f
*
* revised for Plan 9 by K.Okamoto
*/
KouhoList *
getKouhoFile(DicList *dicitem, char * endstr)
{
char *kouhostart, *kouhoend;
KouhoList *kouhoitem, *currntkouhoitem=0, *prevkouhoitem;
prevkouhoitem = 0;
kouhostart = endstr + 1;
while((kouhoend = utfutf(kouhostart, " ")) ||
(kouhoend = utfutf(kouhostart, "\n"))) {
*kouhoend = '\0';
kouhoitem = (KouhoList*)malloc(sizeof(KouhoList)+(kouhoend-kouhostart+1));
kouhoitem->nextkouho = 0;
kouhoitem->prevkouho = prevkouhoitem;
kouhoitem->dicitem = dicitem;
strcpy(kouhoitem->kouhotop, kouhostart);
if (prevkouhoitem)
prevkouhoitem->nextkouho = kouhoitem;
else
currntkouhoitem = kouhoitem;
prevkouhoitem = kouhoitem;
kouhostart = kouhoend + 1;
}
return currntkouhoitem;
}
/*
* get matched kouho from the hash table of header word of the dict
* if found, returns pointer to the first candidate in the hash table.
* if not found, returns 0.
*
* from getCand() in skklib.c by Akinori Ito et al.,(aito@ei5sun.yz.yamagata-u.ac.jp)
*/
KouhoList *
getKouhoHash(Dictionary *dic, char *s)
{
int l, v;
Hash *h;
l = strlen(s);
v = hashVal(s);
for (h = dic->dhash[v]; h != 0; h = h->next) {
if (h->length != l ||
strcmp(h->dicindex->kanahead, s)) continue;
return h->dicindex->kouho; /* return matched kouho */
}
return 0;
}
/*
* from skklib.c by Akinori Ito et al.,(aito@ei5sun.yz.yamagata-u.ac.jp)
* just modified to read easier for current purpose
*/
void
selectKouho(KouhoList **first, KouhoList *current)
{
/* take off currentkouho from the kouholist table */
if (current->prevkouho) {
current->prevkouho->nextkouho = current->nextkouho;
if (current->nextkouho)
current->nextkouho->prevkouho = current->prevkouho;
current->prevkouho = 0;
}
/* take place of firstkouho by currentkouho */
if (*first != current) {
(*first)->prevkouho = current;
current->nextkouho = *first;
*first = current;
}
}

41
sys/src/cmd/ktrans/jisho.h Normal file
View File

@ -0,0 +1,41 @@
/*
* Kenji Okamoto August 4, 2000
* Osaka Prefecture Univ.
* okamoto@granite.cias.osakafu-u.ac.jp
*/
#define HASHSIZE 257
/*
* Structure for Dictionary's header word (in Hiragana)
*/
typedef struct DicList DicList;
struct DicList {
struct KouhoList *kouho;
struct DicList *nextitem; /* for a future extension */
char kanahead[1];
};
/*
* Structure for Kouho of each index word in the dictionary
*/
typedef struct KouhoList KouhoList;
struct KouhoList {
struct KouhoList *nextkouho;
struct KouhoList *prevkouho;
struct DicList *dicitem;
char kouhotop[1]; /* top of the kouhos */
} ;
typedef struct Hash Hash;
struct Hash {
DicList *dicindex; /* pointer to a KouhoList and kanahead etc */
short length;
struct Hash *next;
};
typedef struct Dictionary Dictionary;
struct Dictionary {
DicList *dlist; /* for a future extension, having more than one dictionaries */
Hash *dhash[HASHSIZE];
};

2865
sys/src/cmd/ktrans/ktrans.h Normal file
View File

File diff suppressed because it is too large Load Diff

471
sys/src/cmd/ktrans/main.c Normal file
View File

@ -0,0 +1,471 @@
/*
* Mostly based on the original source codes of Plan 9 release 2
* distribution.
* by Kenji Okamoto, August 4 2000
* Osaka Prefecture Univ.
* okamoto@granite.cias.osakafu-u.ac.jp
*/
#include <u.h>
#include <libc.h>
#include <bio.h>
#include "ktrans.h"
#include "jisho.h"
#define LSIZE 256
Rune lbuf[LSIZE]; /* hiragana buffer for key input written by send() */
Map *table = hira; /* default language conversion table */
uchar okurigana[LSIZE]; /* buffer for okurigana */
char okuri = 0; /* buffer/flag for capital input char */
int in, out;
int llen, olen, joshi = 0;
int natural = 1; /* not Japanese but English mode */
int changelang(int);
int dotrans(Dictionary*);
int nrune(char *);
void send(uchar *, int);
Map *match(uchar *p, int *nc, Map *table);
extern Dictionary *openQDIC(char *);
extern KouhoList *getKouhoHash(Dictionary*, char *);
extern KouhoList *getKouhoFile(DicList*, char *);
extern void freeQDIC(Dictionary*);
extern void selectKouho(KouhoList **, KouhoList*);
void
kbdopen(void)
{
int n, kinfd, koutfd, fd[2];
char buf[128];
int kbd;
kbd = 1;
if((kinfd = open("/dev/kbd", OREAD)) < 0){
kbd = 0;
if((kinfd = open("/dev/cons", OREAD)) < 0)
sysfatal("open kbd: %r");
}
if(bind("#|", "/n/temp", MREPL) < 0)
sysfatal("bind /n/temp: %r");
if((koutfd = open("/n/temp/data1", OWRITE)) < 0)
sysfatal("open kbd pipe: %r");
if(bind("/n/temp/data", kbd? "/dev/kbd": "/dev/cons", MREPL) < 0)
sysfatal("bind kbd pipe: %r");
unmount(nil, "/n/temp");
if(!kbd){
in = kinfd;
out = koutfd;
return;
}
if(pipe(fd) < 0)
sysfatal("pipe: %r");
if(fork()){
in = out = fd[0];
close(fd[1]);
close(kinfd);
close(koutfd);
return;
}
close(fd[0]);
if(fork()){
Biobuf b;
long r;
Binit(&b, fd[1], OREAD);
while((r = Bgetrune(&b)) >= 0){
n = snprint(buf, sizeof(buf), "c%C", (Rune)r)+1;
write(koutfd, buf, n); /* pass on result */
}
} else
while((n = read(kinfd, buf, sizeof(buf))) > 0){
buf[n-1] = 0;
if(n < 2 || buf[0] != 'c')
write(koutfd, buf, n); /* pass on */
else
write(fd[1], buf+1, n-2); /* to translator */
}
exits(nil);
}
void
usage(void)
{
fprint(2, "usage: %s\n", argv0);
exits("usage");
}
void
main(int argc, char *argv[])
{
uchar *bp, *ep, buf[128];
Map *mp;
int nchar, wantmore;
int n, c;
char *dictname;
Dictionary *jisho;
ARGBEGIN{
default: usage();
}ARGEND;
if(argc != 0)
usage();
if((dictname = getenv("jisho")) == nil)
dictname = "/lib/kanji.jisho";
jisho = openQDIC(dictname);
kbdopen();
if(fork())
exits(nil); /* parent process will exit */
bp = ep = buf;
wantmore = 0;
for (;;) { /* key board input loop */
getmore:
if (bp>=ep || wantmore) {
if (wantmore==0)
bp = ep = buf; /* clear all */
n = read(in, ep, &buf[sizeof(buf)]-ep);
if (n<=0)
exits("");
ep += n;
*ep = '\0';
}
while (bp<ep) { /* there are input data */
if (table == hira && natural != 1 && (*bp>'A' && *bp<='Z') && ep-bp<2
&& !strchr("EIOU", *bp)) {
wantmore = 1;
goto getmore;
}
if (!fullrune((char *)bp, ep-bp)) { /* not enough length of input */
wantmore = 1;
goto getmore;
}
wantmore = 0;
if (*bp=='') { /* ^x read ktrans-jisho once more */
freeQDIC(jisho);
jisho = openQDIC(dictname);
llen = 0;
olen = okuri = joshi = 0;
wantmore=0;
bp=ep=buf;
continue;
}
if (*bp=='') { /* ^\ (start translation command) */
c = dotrans(jisho);
if (c)
*bp = c; /* pointer to translated rune */
else
bp++;
continue;
}
if (*bp==' ') { /* ^l (no translate command) */
bp++;
llen = 0;
olen = okuri = joshi = 0;
continue;
}
if (changelang(*bp)) { /* change language mode OK */
bp++;
olen = okuri = joshi = 0;
continue;
}
if (natural || *bp<=' ' || *bp>='{') { /* English mode but not ascii */
Rune r;
int rlen = chartorune(&r, (char *)bp);
send(bp, rlen); /* write bp to /dev/cons */
bp += rlen;
continue;
}
if (table == hira && (*bp >= 'A' && *bp <= 'Z') && (*(bp+1) < 'A'
|| *(bp+1) > 'Z')) {
*bp = okuri = tolower(*bp);
joshi = olen = 0;
} else if (table == hira && (*bp >= 'A' && *bp <= 'Z') &&
(*(bp+1) >= 'A' && *(bp+1) <= 'Z')) {
*bp = okuri = tolower(*bp);
*(bp+1) = tolower(*(bp+1));
joshi = 1;
olen = 0;
}
mp = match(bp, &nchar, table);
if (mp == 0) {
if (nchar>0) { /* match, longer possible */
wantmore++;
break;
}
send(bp++, 1); /* alphabet in kana mode */
} else {
send((uchar*)mp->kana, strlen(mp->kana));
bp += nchar;
}
}
}
}
int
min(int a, int b)
{
return a<b? a: b;
}
/*
* send UTF string (p) with length (n) to stdout
* and write rune (r) in global lbuf[] buffer
* or okurigana[] buffer if okuri (verb or joshi) mode
*/
void
send(uchar *p, int n)
{
Rune r;
uchar *ep;
if (write(out, (char*)p, n) != n)
sysfatal("write: %r");
if (llen>LSIZE-64) {
memmove((char*)lbuf, (char*)lbuf+64, 64*sizeof(Rune));
llen -= 64;
}
if (table!=hira || natural)
return;
ep = p+n;
if(okuri)
while (olen<LSIZE && p<ep)
okurigana[olen++] = *p++;
else
while (llen<LSIZE && p<ep) {
p += chartorune(&r, (char*)p);
if (r=='\b') {
if (llen>0)
llen--;
continue;
}
if (r==0x80) /* ignore view key */
continue;
lbuf[llen++] = r;
}
}
/*
* Romaji to Hiragana/Katakana conversion
* romaji shoud be input as small letter
* returns the matched address in table, hira, kata, etc.
* nc: number of character (return value)
*/
Map *
match(uchar *p, int *nc, Map *table)
{
register Map *longp = 0, *kp;
static char last;
int longest = 0;
*nc = -1;
for (kp=table; kp->roma; kp++) {
if (*p == *kp->roma) {
int lr = strlen(kp->roma);
int len = min(lr, strlen((char *)p));
if (strncmp(kp->roma, (char *)p, len)==0) {
if (len<lr) {
*nc = 1;
return 0;
}
if (len>longest) {
longest = len;
longp = kp;
}
}
}
}
if (longp) {
last = longp->roma[longest-1];
*nc = longp->advance;
}
return longp;
}
int
changelang(int c)
{
switch(c){
case '': /* ^t (English mode) */
natural = 1;
llen = 0;
return 1;
break;
case '': /* ^n (Japanese hiragana mode ) */
natural = 0;
table = hira;
llen = 0;
return 1;
break;
case ' ': /* ^k (Japanese katakana mode) */
natural = 0;
table = kata;
llen = 0;
return 1;
break;
case '': /* ^r (Russian mode) */
natural = 0;
table = cyril;
llen = 0;
return 1;
break;
case '': /* ^o (Greek mode) */
natural = 0;
table = greek;
llen = 0;
return 1;
break;
case '': /* ^s (Korean mode) */
natural = 0;
table = hangul;
llen = 0;
return 1;
break;
}
return 0;
}
/*
* write translated kanji runes to stdout and return last character
* if it's not ctl-\. if the last is ctl-\, proceed with
* translation of the next kouho
*/
int
dotrans(Dictionary *dic)
{
Rune *res, r[1];
char v[1024], *p, tbuf[64], hirabuf[64];
int j, lastlen, nokouho = 0;
char ch;
KouhoList *fstkouho, *currentkouho;
if (llen==0)
return 0; /* don't use kanji transform function */
if (okuri && joshi != 1) {
lbuf[llen++] = (Rune)okuri;
lbuf[llen] = 0;
}else
lbuf[llen] = 0;
okurigana[olen] = 0;
/*
* search the matched index for the key word in the dict hash table, and
* return a pointer to the matched kouho, 0 otherwise.
*/
res = lbuf;
for (j=0; *res != L'\0'; j += runetochar(v+j, res++))
;
v[j] = '\0';
strcpy(tbuf, v);
strcpy(hirabuf, v); /* to remember the initial hiragana input */
if (okuri && joshi != 1) /* verb mode */
hirabuf[strlen(hirabuf) - 1] = '\0';
if(!(fstkouho = getKouhoHash(dic, v))) { /* not found */
llen = olen = okuri = joshi = 0;
okurigana[0] = 0;
return 0;
}
currentkouho = fstkouho;
for(;;) {
p = currentkouho->kouhotop; /* p to the head of kanji kouho array */
lastlen = nrune(tbuf); /* number of rune chars */
if (okuri && joshi != 1) /* verb mode */
for (j=0; j<lastlen-1; j++)
write(out, "\b", 1); /* clear hiragana input */
else
for (j=0; j<lastlen; j++)
write(out, "\b", 1); /* clear hiragana input */
if (okuri) {
lastlen = nrune((char *)okurigana);
for (j=0; j<lastlen; j++)
write(out, "\b", 1);
}
write(out, p, strlen(p)); /* write kanji to stdout */
if (okuri)
write(out, (char *)okurigana, olen);
if (read(in, &ch, 1)<=0) /* read from stdin */
exits(nil);
if (ch == '') { /* if next input is ^\, once again */
if(currentkouho->nextkouho != 0) { /* have next kouho */
nokouho = 0;
strcpy(tbuf, p);
currentkouho = currentkouho->nextkouho;
if (okuri && joshi != 1) /* verb mode */
for (j=0; j<nrune(tbuf); j++)
write(out, "\b", 1);
continue;
} else { /* the last kouho */
if (okuri) {
lastlen = nrune((char *)okurigana);
for (j=0; j<lastlen; j++)
write(out, "\b", 1);
}
for (lastlen=0; *p != 0; p += j) {
j = chartorune(r, p);
lastlen++;
}
for (j=0; j<lastlen; j++)
write(out, "\b", 1);
if(hirabuf[0])
write(out, hirabuf, strlen(hirabuf));
if(okurigana[0])
write(out, (char *)okurigana, olen);
olen = okuri = joshi = 0;
okurigana[0] = 0;
break;
}
} else {
if(!nokouho) /* learn the previous use of the kouho */
selectKouho(&(fstkouho->dicitem->kouho), currentkouho);
olen = okuri = joshi = 0;
okurigana[0] = 0;
break;
}
}
llen = 0;
return ch;
}
/*
* returns the number of characters in the pointed Rune
*/
int
nrune(char *p)
{
int n = 0;
Rune r;
while (*p) {
p += chartorune(&r, p);
n++;
}
return n;
}

10
sys/src/cmd/ktrans/mkfile Normal file
View File

@ -0,0 +1,10 @@
</$objtype/mkfile
BIN=/$objtype/bin
TARG=ktrans
HFILES=jisho.h ktrans.h
OFILES=\
main.$O\
jisho.$O
</sys/src/cmd/mkone