Tera TermRevision: 8766
https://osdn.net/projects/ttssh2/scm/svn/commits/8766
Author: zmatsuo
Date: 2020-05-06 23:52:04 +0900 (Wed, 06 May 2020)
Log Message:
-----------
CJK,2byte文字の入力をできるようにした
- 2byte系
- KS5601, CP51949, ハングル
- CP936, GB2312
- CP950, Big5
- KanjiCode2List(), List2KanjiCode() を ttlib.c から ttdlg.c へ移動
- IdChinese (tttype.h) 追加
- コードページやロケールの設定なしにメニューから設定できるようにする
- struct tttset に UnicodeAmbiguousAsWide 追加
- UnicodeAmbiguousWide=ON/OFF を teraterm.ini に追加
Modified Paths:
--------------
trunk/teraterm/common/ttlib.c
trunk/teraterm/common/ttlib.h
trunk/teraterm/common/tttypes.h
trunk/teraterm/teraterm/buffer.c
trunk/teraterm/teraterm/vtterm.c
trunk/teraterm/ttpdlg/ttdlg.c
trunk/teraterm/ttpset/ttset.c
-------------- next part --------------
Modified: trunk/teraterm/common/ttlib.c
===================================================================
--- trunk/teraterm/common/ttlib.c 2020-05-06 14:51:43 UTC (rev 8765)
+++ trunk/teraterm/common/ttlib.c 2020-05-06 14:52:04 UTC (rev 8766)
@@ -1529,53 +1529,28 @@
return CDSIZEOF_STRUCT(OPENFILENAMEW,lpTemplateName);
}
-// convert table for KanjiCodeID and ListID
-// cf. KanjiList,KanjiListSend
-// KoreanList,KoreanListSend
-// Utf8List,Utf8ListSend
-// IdSJIS, IdEUC, IdJIS, IdUTF8, IdUTF8m
-// IdEnglish, IdJapanese, IdRussian, IdKorean, IdUtf8
-/* KanjiCode2List(Language,KanjiCodeID) returns ListID */
-int KanjiCode2List(int lang, int kcode)
-{
- int Table[5][5] = {
- {1, 2, 3, 4, 5}, /* English (dummy) */
- {1, 2, 3, 4, 5}, /* Japanese(dummy) */
- {1, 2, 3, 4, 5}, /* Russian (dummy) */
- {1, 1, 1, 2, 3}, /* Korean */
- {1, 1, 1, 1, 2}, /* Utf8 */
- };
- lang--;
- kcode--;
- return Table[lang][kcode];
-}
-/* List2KanjiCode(Language,ListID) returns KanjiCodeID */
-int List2KanjiCode(int lang, int list)
-{
- int Table[5][5] = {
- {1, 2, 3, 4, 5}, /* English (dummy) */
- {1, 2, 3, 4, 5}, /* Japanese(dummy) */
- {1, 2, 3, 4, 5}, /* Russian (dummy) */
- {1, 4, 5, 1, 1}, /* Korean */
- {4, 5, 4, 4, 4}, /* Utf8 */
- };
- lang--;
- list--;
- if (list < 0) {
- list = 0;
- }
- return Table[lang][list];
-}
-/* KanjiCodeTranslate(Language(dest), KanjiCodeID(source)) returns KanjiCodeID */
+/**
+ * KanjiCodeTranslate(Language(dest), KanjiCodeID(source)) returns KanjiCodeID
+ * @param[in] lang (IdEnglish, IdJapanese, IdRussian, ...)
+ * @param[in] kcode (IdSJIS, IdEUC, ... IdKOI8 ... )
+ * @return lang\x82ɑ\xB6\x8D݂\xB7\x82銿\x8E\x9A\x83R\x81[\x83h\x82\xF0\x95Ԃ\xB7
+ *
+ * lang\x82ɑ\xB6\x8D݂\xB5\x82Ȃ\xA2\x8A\xBF\x8E\x9A\x83R\x81[\x83h\x82\xF0\x8Eg\x97p\x82\xB5\x82Ȃ\xA2\x82悤\x82\xB1\x82̊\x94\x82\xF0\x8Eg\x97p\x82\xB7\x82\xE9
+ * - ini\x83t\x83@\x83C\x83\x8B\x82̓ǂݍ\x9E\x82ݎ\x9E
+ * - \x90ݒ\xE8\x82\xC5lang\x82\xF0\x90\xE8\x91ւ\xA6\x82\xBD\x8E\x9E
+ */
int KanjiCodeTranslate(int lang, int kcode)
{
- int Table[5][5] = {
+ static const int Table[][5] = {
{1, 2, 3, 4, 5}, /* to English (dummy) */
{1, 2, 3, 4, 5}, /* to Japanese(dummy) */
{1, 2, 3, 4, 5}, /* to Russian (dummy) */
{1, 1, 1, 4, 5}, /* to Korean */
{4, 4, 4, 4, 5}, /* to Utf8 */
+ {1, 2, 2, 2, 2}, /* to Chinese */
};
+ if (lang < 1 || lang > IdLangMax) lang = 1;
+ if (kcode < 1 || kcode > 5) kcode = 1;
lang--;
kcode--;
return Table[lang][kcode];
Modified: trunk/teraterm/common/ttlib.h
===================================================================
--- trunk/teraterm/common/ttlib.h 2020-05-06 14:51:43 UTC (rev 8765)
+++ trunk/teraterm/common/ttlib.h 2020-05-06 14:52:04 UTC (rev 8766)
@@ -101,8 +101,6 @@
DllExport BOOL HasGetAdaptersAddresses();
DllExport BOOL HasDnsQuery();
DllExport BOOL HasBalloonTipSupport();
-int KanjiCode2List(int lang, int kcode);
-int List2KanjiCode(int lang, int kcode);
int KanjiCodeTranslate(int lang, int kcode);
DllExport char *mctimelocal(char *format, BOOL utc_flag);
char *strelapsed(DWORD start_time);
Modified: trunk/teraterm/common/tttypes.h
===================================================================
--- trunk/teraterm/common/tttypes.h 2020-05-06 14:51:43 UTC (rev 8765)
+++ trunk/teraterm/common/tttypes.h 2020-05-06 14:52:04 UTC (rev 8766)
@@ -189,7 +189,8 @@
#define IdRussian 3
#define IdKorean 4 //HKS
#define IdUtf8 5
-#define IdLangMax IdUtf8
+#define IdChinese 6
+#define IdLangMax IdChinese
// LogDialog Option
#define LOGDLG_BINARY 1
@@ -678,6 +679,7 @@
int ConfigVersion;
int RunningVersion;
DWORD SelectStartDelay;
+ WORD UnicodeAmbiguousAsWide;
};
typedef struct tttset TTTSet, *PTTSet;
@@ -703,12 +705,19 @@
#define IdVT525 12
/* Kanji Code ID */
+ /* ts.KanjiCode, ts.KanjiCodeSend \x82̒l */
+
+// ts.Language == IdEnglish
+#define IdCodeEnglish 1
+
+// ts.Language == IdJapanese
#define IdSJIS 1
#define IdEUC 2
#define IdJIS 3
-#define IdUTF8 4
+#define IdUTF8 4 // IdUtf8 (\x8F\xAC\x95\xB6\x8E\x9A)\x82\xCD ts.Language \x97p
#define IdUTF8m 5
+// ts.Language == IdRussian
// Russian code sets
#define IdWindows 1
#define IdKOI8 2
@@ -715,6 +724,15 @@
#define Id866 3
#define IdISO 4
+// ts.Language == IdKorean
+// Korean
+#define IdKoreanCP51949 1 // CP51949, KS5601
+
+// ts.Language == IdChinese
+// China
+#define IdCnGB2312 1 // 1 CP936, GB2312
+#define IdCnBig5 2 // 2 CP950, Big5
+
/* KanjiIn modes */
#define IdKanjiInA 1
#define IdKanjiInB 2
Modified: trunk/teraterm/teraterm/buffer.c
===================================================================
--- trunk/teraterm/teraterm/buffer.c 2020-05-06 14:51:43 UTC (rev 8765)
+++ trunk/teraterm/teraterm/buffer.c 2020-05-06 14:52:04 UTC (rev 8766)
@@ -57,7 +57,7 @@
typedef struct {
char32_t u32;
char32_t u32_last;
- char WidthProperty; // 'W' or 'F' or 'H' or 'A' (\x95\xB6\x8E\x9A\x82̑\xAE\x90\xAB)
+ char WidthProperty; // 'W' or 'F' or 'H' or 'A' or 'n'(Narrow) or 'N'(Neutual) (\x95\xB6\x8E\x9A\x82̑\xAE\x90\xAB)
char HalfWidth; // TRUE/FALSE = \x94\xBC\x8Ap/\x91S\x8Ap (\x95\\x8E\xA6\x82\xB7\x82\xE9\x82Ƃ\xAB\x82̕\xB6\x8E\x9A\x95\x9D)
char Padding; // TRUE = \x91S\x8Ap\x82̎\x9F\x82̋l\x82ߕ\xA8 or \x8Ds\x96\x96\x82̋l\x82ߕ\xA8
char Emoji; // TRUE = \x8AG\x95\xB6\x8E\x9A
@@ -2209,12 +2209,13 @@
}
}
-static BOOL BuffIsHalfWidthFromCode(TTTSet *ts_, unsigned int u32, char *width_property, char *emoji)
+static BOOL BuffIsHalfWidthFromCode(const TTTSet *ts_, unsigned int u32, char *width_property, char *emoji)
{
*width_property = UnicodeGetWidthProperty(u32);
*emoji = (char)UnicodeIsEmoji(u32);
if (*emoji) {
- if (ts_->Language == IdJapanese) {
+ //if (ts_->Language == IdJapanese) {
+ if (ts_->UnicodeAmbiguousAsWide) {
// \x91S\x8Ap
return FALSE;
} else {
@@ -2475,9 +2476,6 @@
// \x8C\xBB\x8D\xDDx\x82\xAA\x88\xEA\x94ԉE?
if ((cur_y + 1) < NumOfLines) {
if ((CodeLineW[x].attr & AttrLineContinued) != 0) {
- if ((cur_y + 1) == 24) {
- int a = 0;
- }
const LONG TmpPtr = GetLinePtr(PageStart + cur_y + 1);
if ((CodeLineW[TmpPtr + NumOfColumns - 1].attr & AttrURL) != 0) {
next = TRUE;
@@ -3158,7 +3156,6 @@
bufW[lenW] = b->wc2[1];
bufWW[lenW] = '0';
lenW++;
-// DrawFlag = TRUE; // \x82\xB7\x82\xAE\x82ɕ`\x89悷\x82\xE9
}
if (b->CombinationCharCount16 != 0)
{
@@ -3183,6 +3180,10 @@
bufA[lenA] = ansi_char & 0xff;
lenA++;
}
+
+ if (b->WidthProperty == 'A' || b->WidthProperty == 'N') {
+ DrawFlag = TRUE;
+ }
}
// \x8DŌ\xE3\x82܂ŃX\x83L\x83\x83\x83\x93\x82\xB5\x82\xBD?
Modified: trunk/teraterm/teraterm/vtterm.c
===================================================================
--- trunk/teraterm/teraterm/vtterm.c 2020-05-06 14:51:43 UTC (rev 8765)
+++ trunk/teraterm/teraterm/vtterm.c 2020-05-06 14:52:04 UTC (rev 8766)
@@ -63,7 +63,7 @@
#include "unicode_test.h"
-void ParseFirst(BYTE b);
+static void ParseFirst(BYTE b);
#define Accept8BitCtrl ((VTlevel >= 2) && (ts.TermFlag & TF_ACCEPT8BITCTRL))
@@ -921,23 +921,40 @@
// codepage\x88ꗗ
// https://docs.microsoft.com/en-us/openspecs/windows_protocols/ms-ucoderef/28fefe92-d66c-4b03-90a9-97b473223d43
unsigned long u32 = 0;
- if (ts.Language == IdKorean && ts.CodePage == 51949) {
-#if 0
- unsigned char buf[2];
- int ret;
- wchar_t wchar;
- buf[0] = Kanji >> 8;
- buf[1] = Kanji & 0xff;
- ret = MultiByteToWideChar(51949, MB_ERR_INVALID_CHARS, (char *)buf, 2, &wchar, 1);
- u32 = wchar;
-#endif
- u32 = MBCP_UTF32(Kanji, ts.CodePage);
- } else if (ts.Language == IdJapanese && ts.CodePage == 932) {
+ switch (ts.Language) {
+ case IdJapanese:
// \x82\xB1\x82\xB1\x82ɗ\x88\x82\xBD\x8E\x9E\x93_\x82\xC5CP932\x82ɂȂ\xC1\x82Ă\xA2\x82\xE9
- //} else if (ts.KanjiCode == IdSJIS || ts.KanjiCode == IdEUC || ts.KanjiCode == IdJIS) {
u32 = CP932ToUTF32(Kanji);
- } else {
+ break;
+ case IdKorean:
+ if (ts.KanjiCode == IdKoreanCP51949) {
+ // CP51949
+ u32 = MBCP_UTF32(Kanji, 51949);
+ }
+ else {
+ assert(FALSE);
+ goto default_;
+ }
+ break;
+ case IdChinese:
+ if (ts.KanjiCode == IdCnGB2312) {
+ // CP936 GB2312
+ u32 = MBCP_UTF32(Kanji, 936);
+ }
+ else if (ts.KanjiCode == IdCnBig5) {
+ // CP950 Big5
+ u32 = MBCP_UTF32(Kanji, 950);
+ }
+ else {
+ assert(FALSE);
+ goto default_;
+ }
+ break;
+ default:
+ default_:
+ assert(FALSE);
u32 = MBCP_UTF32(Kanji, ts.CodePage);
+ break;
}
CharAttrTmp.AttrEx = CharAttrTmp.Attr;
BuffPutUnicode(u32, CharAttrTmp, InsertMode);
@@ -5391,27 +5408,109 @@
}
/**
- * dbcs\x82\xCC1byte\x96ڃ`\x83F\x83b\x83N?
+ * IsDBCSLeadByteEx() \x82Ƃقړ\xAF\x82\xB6
+ * ismbblead() \x82̊g\x92\xA3
*/
+int __ismbblead(BYTE b, int code_page)
+{
+ switch (code_page) {
+ case 932:
+ // \x93\xFA\x96{\x8C\xEA shift jis
+ if (((0x81 <= b) && (b <= 0x9f)) || ((0xe0 <= b) && (b <= 0xfc))) {
+ return TRUE;
+ }
+ return FALSE;
+ case 51949:
+ // Korean CP51949
+ if ((0xA1 <= b) && (b <= 0xFE)) {
+ return TRUE;
+ }
+ return FALSE;
+ case 936:
+ // CP936 GB2312
+ if ((0xA1 <= b) && (b <= 0xFE)) {
+ return TRUE;
+ }
+ return FALSE;
+ case 950:
+ // CP950 Big5
+ if (((0xA1 <= b) && (b <= 0xc6)) || ((0xc9 <= b) && (b <= 0xf9))) {
+ return TRUE;
+ }
+ return FALSE;
+ default:
+ break;
+ }
+ return FALSE;
+}
+
+/**
+ * ismbbtrail() \x82̊g\x92\xA3
+ */
+int __ismbbtrail(BYTE b, int code_page)
+{
+ switch (code_page) {
+ case 932:
+ if (((0x40 <= b) && (b <= 0x7E)) || ((0x80 <= b) && (b <= 0xFC))) {
+ return TRUE;
+ }
+ return FALSE;
+ case 51949:
+ // Korean CP51949
+ if ((0xA1 <= b) && (b <= 0xFE)) {
+ return TRUE;
+ }
+ return FALSE;
+ case 936:
+ // CP936 GB2312
+ if ((0xA1 <= b) && (b <= 0xFE)) {
+ return TRUE;
+ }
+ return FALSE;
+ case 950:
+ // CP950 Big5
+ if (((0x40 <= b) && (b <= 0x7e)) || ((0xa1 <= b) && (b <= 0xfe))) {
+ return TRUE;
+ }
+ return FALSE;
+ default:
+ break;
+ }
+ return FALSE;
+}
+
+/**
+ * 1byte\x96ڃ`\x83F\x83b\x83N
+ */
+static BOOL CheckFirstByte(BYTE b, int lang, int kanji_code)
+{
+ switch (lang) {
+ case IdKorean:
+ return __ismbblead(b, 51949);
+ case IdChinese:
+ if (kanji_code == IdCnGB2312) {
+ return __ismbblead(b, 936);
+ }
+ else if (ts.KanjiCode == IdCnBig5) {
+ return __ismbblead(b, 950);
+ }
+ break;
+ default:
+ assert(FALSE);
+ break;
+ }
+ assert(FALSE);
+ return FALSE;
+}
+
+/**
+ * ts.Language == IdJapanese \x8E\x9E
+ * 1byte\x96ڃ`\x83F\x83b\x83N
+ */
static BOOL CheckKanji(BYTE b)
{
BOOL Check;
-#if UNICODE_INTERNAL_BUFF
- if (ts.CodePage != 932) {
- // TODO \x82\xBF\x82\xE1\x82\xF1\x82ƃ`\x83F\x83b\x83N\x82\xB7\x82\xE9
- // IsDBCSLeadByteEx() \x82\xAA\x91Ó\x96?
- if (ts.CodePage == 936) {
- // chs
- return ((0x81 <= b) && (b <= 0xfe));
- }
- if (ts.CodePage == 950) {
- // cht
- return ((0x88 <= b) && (b <= 0xfe));
- }
-
- }
-#endif
if (ts.Language!=IdJapanese)
return FALSE;
@@ -5449,24 +5548,6 @@
return Check;
}
-BOOL CheckKorean(BYTE b)
-{
- BOOL Check;
- if (ts.Language!=IdKorean)
- return FALSE;
-
- if (ts.KanjiCode == IdSJIS) {
- if ((0xA1<=b) && (b<=0xFE)) {
- Check = TRUE;
- }
- else {
- Check = FALSE;
- }
- }
-
- return Check;
-}
-
static BOOL ParseFirstJP(BYTE b)
// returns TRUE if b is processed
// (actually allways returns TRUE)
@@ -5617,7 +5698,7 @@
return TRUE;
}
-BOOL ParseFirstKR(BYTE b)
+static BOOL ParseFirstKR(BYTE b)
// returns TRUE if b is processed
// (actually allways returns TRUE)
{
@@ -5640,7 +5721,7 @@
}
}
- if ((!KanjiIn) && CheckKorean(b)) {
+ if ((!KanjiIn) && CheckFirstByte(b, ts.Language, ts.KanjiCode)) {
Kanji = b << 8;
KanjiIn = TRUE;
return TRUE;
@@ -5680,6 +5761,69 @@
return TRUE;
}
+static BOOL ParseFirstCn(BYTE b)
+// returns TRUE if b is processed
+// (actually allways returns TRUE)
+{
+ if (KanjiIn) {
+ // TODO
+ if ((0x40<=b) && (b<=0x7e) ||
+ (0xa1<=b) && (b<=0xFE))
+ {
+ PutKanji(b);
+ KanjiIn = FALSE;
+ return TRUE;
+ }
+ else if ((ts.TermFlag & TF_CTRLINKANJI)==0) {
+ KanjiIn = FALSE;
+ }
+ else if ((b==CR) && Wrap) {
+ CarriageReturn(FALSE);
+ LineFeed(LF,FALSE);
+ Wrap = FALSE;
+ }
+ }
+
+ if ((!KanjiIn) && CheckFirstByte(b, ts.Language, ts.KanjiCode)) {
+ Kanji = b << 8;
+ KanjiIn = TRUE;
+ return TRUE;
+ }
+
+ if (b<=US) {
+ ParseControl(b);
+ }
+ else if (b==0x20) {
+ PutChar(b);
+ }
+ else if ((b>=0x21) && (b<=0x7E)) {
+// if (Gn[Glr[0]] == IdKatakana) {
+// b = b | 0x80;
+// }
+ PutChar(b);
+ }
+ else if (b==0x7f) {
+ return TRUE;
+ }
+ else if ((0x80<=b) && (b<=0x9F)) {
+ ParseControl(b);
+ }
+ else if (b==0xA0) {
+ PutChar(0x20);
+ }
+ else if ((b>=0xA1) && (b<=0xFE)) {
+ if (Gn[Glr[1]] == IdASCII) {
+ b = b & 0x7f;
+ }
+ PutChar(b);
+ }
+ else {
+ PutChar(b);
+ }
+
+ return TRUE;
+}
+
static void ParseASCII(BYTE b)
{
#if !UNICODE_INTERNAL_BUFF
@@ -6099,7 +6243,7 @@
return FALSE;
}
-void ParseFirst(BYTE b)
+static void ParseFirst(BYTE b)
{
switch (ts.Language) {
case IdUtf8:
@@ -6144,12 +6288,17 @@
}
break;
-
case IdRussian:
if (ParseFirstRus(b)) {
return;
}
break;
+
+ case IdChinese:
+ if (ParseFirstCn(b)) {
+ return;
+ }
+ break;
}
if (SSflag) {
Modified: trunk/teraterm/ttpdlg/ttdlg.c
===================================================================
--- trunk/teraterm/ttpdlg/ttdlg.c 2020-05-06 14:51:43 UTC (rev 8765)
+++ trunk/teraterm/ttpdlg/ttdlg.c 2020-05-06 14:52:04 UTC (rev 8766)
@@ -122,6 +122,45 @@
"14400","19200","38400","57600","115200",
"230400", "460800", "921600", NULL};
+// convert table for KanjiCodeID and ListID
+// cf. KanjiList,KanjiListSend
+// KoreanList,KoreanListSend
+// Utf8List,Utf8ListSend
+// IdSJIS, IdEUC, IdJIS, IdUTF8, IdUTF8m
+// IdEnglish, IdJapanese, IdRussian, IdKorean, IdUtf8
+/* KanjiCode2List(Language,KanjiCodeID) returns ListID */
+static int KanjiCode2List(int lang, int kcode)
+{
+ int Table[5][5] = {
+ {1, 2, 3, 4, 5}, /* English (dummy) */
+ {1, 2, 3, 4, 5}, /* Japanese(dummy) */
+ {1, 2, 3, 4, 5}, /* Russian (dummy) */
+ {1, 1, 1, 2, 3}, /* Korean */
+ {1, 1, 1, 1, 2}, /* Utf8 */
+ };
+ lang--;
+ kcode--;
+ return Table[lang][kcode];
+}
+
+/* List2KanjiCode(Language,ListID) returns KanjiCodeID */
+static int List2KanjiCode(int lang, int list)
+{
+ int Table[5][5] = {
+ {1, 2, 3, 4, 5}, /* English (dummy) */
+ {1, 2, 3, 4, 5}, /* Japanese(dummy) */
+ {1, 2, 3, 4, 5}, /* Russian (dummy) */
+ {1, 4, 5, 1, 1}, /* Korean */
+ {4, 5, 4, 4, 4}, /* Utf8 */
+ };
+ lang--;
+ list--;
+ if (list < 0) {
+ list = 0;
+ }
+ return Table[lang][list];
+}
+
/*
* COM\x83|\x81[\x83g\x82Ɋւ\xB7\x82\xE9\x8Fڍ\xEE\x95\xF1
*/
Modified: trunk/teraterm/ttpset/ttset.c
===================================================================
--- trunk/teraterm/ttpset/ttset.c 2020-05-06 14:51:43 UTC (rev 8765)
+++ trunk/teraterm/ttpset/ttset.c 2020-05-06 14:52:04 UTC (rev 8766)
@@ -2241,6 +2241,9 @@
ReadFont3("Tera Term", "DlgFont", NULL, FName,
ts->DialogFontName, sizeof(ts->DialogFontName),
&ts->DialogFontPoint, &ts->DialogFontCharSet);
+
+ // Unicode\x90ݒ\xE8
+ ts->UnicodeAmbiguousAsWide = GetOnOff(Section, "UnicodeAmbiguousWide", FName, TRUE);
}
void PASCAL WriteIniFile(PCHAR FName, PTTSet ts)
@@ -3563,6 +3566,9 @@
ts->DialogFontPoint,
ts->DialogFontCharSet);
WritePrivateProfileStringA("Tera Term", "DlgFont", Temp, FName);
+
+ // Unicode\x90ݒ\xE8
+ WriteOnOff(Section, "UnicodeAmbiguousWide", FName, ts->UnicodeAmbiguousAsWide);
}
#define VTEditor "VT editor keypad"