--- np2/io/gdc_sub.c	2004/02/02 12:16:30	1.7
+++ np2/io/gdc_sub.c	2004/06/02 11:02:53	1.18
@@ -3,6 +3,7 @@
 #include	"cpucore.h"
 #include	"pccore.h"
 #include	"iocore.h"
+#include	"gdc_sub.h"
 #include	"gdc_pset.h"
 #include	"vram.h"
 
@@ -16,20 +17,78 @@ enum {
 typedef struct {
 	SINT16	x;
 	SINT16	y;
-	SINT16	sx;
-	SINT16	sy;
-} TEXTDIR;
+	SINT16	x2;
+	SINT16	y2;
+} VECTDIR;
+
+const UINT32 gdcplaneseg[4] = {VRAM_E, VRAM_B, VRAM_R, VRAM_G};
 
 static	UINT16	gdc_rt[RT_TABLEMAX+1];
 
-static const TEXTDIR textdir[8] = {
+static const VECTDIR vectdir[16] = {
 					{ 0, 1, 1, 0}, { 1, 1, 1,-1},
 					{ 1, 0, 0,-1}, { 1,-1,-1,-1},
 					{ 0,-1,-1, 0}, {-1,-1,-1, 1},
-					{-1, 0, 0, 1}, {-1, 1, 1, 1}};
+					{-1, 0, 0, 1}, {-1, 1, 1, 1},
+
+					{ 0, 1, 1, 1}, { 1, 1, 1, 0},		// SL
+					{ 1, 0, 1,-1}, { 1,-1, 0,-1},
+					{ 0,-1,-1,-1}, {-1,-1,-1, 0},
+					{-1, 0,-1, 1}, {-1, 1, 0, 1}};
+
+
+#if !defined(MEMOPTIMIZE) || (MEMOPTIMIZE < 2)
+const UINT8 gdcbitreverse[0x100] = {
+				0x00, 0x80, 0x40, 0xc0, 0x20, 0xa0, 0x60, 0xe0,
+				0x10, 0x90, 0x50, 0xd0, 0x30, 0xb0, 0x70, 0xf0,
+				0x08, 0x88, 0x48, 0xc8, 0x28, 0xa8, 0x68, 0xe8,
+				0x18, 0x98, 0x58, 0xd8, 0x38, 0xb8, 0x78, 0xf8,
+				0x04, 0x84, 0x44, 0xc4, 0x24, 0xa4, 0x64, 0xe4,
+				0x14, 0x94, 0x54, 0xd4, 0x34, 0xb4, 0x74, 0xf4,
+				0x0c, 0x8c, 0x4c, 0xcc, 0x2c, 0xac, 0x6c, 0xec,
+				0x1c, 0x9c, 0x5c, 0xdc, 0x3c, 0xbc, 0x7c, 0xfc,
+				0x02, 0x82, 0x42, 0xc2, 0x22, 0xa2, 0x62, 0xe2,
+				0x12, 0x92, 0x52, 0xd2, 0x32, 0xb2, 0x72, 0xf2,
+				0x0a, 0x8a, 0x4a, 0xca, 0x2a, 0xaa, 0x6a, 0xea,
+				0x1a, 0x9a, 0x5a, 0xda, 0x3a, 0xba, 0x7a, 0xfa,
+				0x06, 0x86, 0x46, 0xc6, 0x26, 0xa6, 0x66, 0xe6,
+				0x16, 0x96, 0x56, 0xd6, 0x36, 0xb6, 0x76, 0xf6,
+				0x0e, 0x8e, 0x4e, 0xce, 0x2e, 0xae, 0x6e, 0xee,
+				0x1e, 0x9e, 0x5e, 0xde, 0x3e, 0xbe, 0x7e, 0xfe,
+				0x01, 0x81, 0x41, 0xc1, 0x21, 0xa1, 0x61, 0xe1,
+				0x11, 0x91, 0x51, 0xd1, 0x31, 0xb1, 0x71, 0xf1,
+				0x09, 0x89, 0x49, 0xc9, 0x29, 0xa9, 0x69, 0xe9,
+				0x19, 0x99, 0x59, 0xd9, 0x39, 0xb9, 0x79, 0xf9,
+				0x05, 0x85, 0x45, 0xc5, 0x25, 0xa5, 0x65, 0xe5,
+				0x15, 0x95, 0x55, 0xd5, 0x35, 0xb5, 0x75, 0xf5,
+				0x0d, 0x8d, 0x4d, 0xcd, 0x2d, 0xad, 0x6d, 0xed,
+				0x1d, 0x9d, 0x5d, 0xdd, 0x3d, 0xbd, 0x7d, 0xfd,
+				0x03, 0x83, 0x43, 0xc3, 0x23, 0xa3, 0x63, 0xe3,
+				0x13, 0x93, 0x53, 0xd3, 0x33, 0xb3, 0x73, 0xf3,
+				0x0b, 0x8b, 0x4b, 0xcb, 0x2b, 0xab, 0x6b, 0xeb,
+				0x1b, 0x9b, 0x5b, 0xdb, 0x3b, 0xbb, 0x7b, 0xfb,
+				0x07, 0x87, 0x47, 0xc7, 0x27, 0xa7, 0x67, 0xe7,
+				0x17, 0x97, 0x57, 0xd7, 0x37, 0xb7, 0x77, 0xf7,
+				0x0f, 0x8f, 0x4f, 0xcf, 0x2f, 0xaf, 0x6f, 0xef,
+				0x1f, 0x9f, 0x5f, 0xdf, 0x3f, 0xbf, 0x7f, 0xff};
+#else
+REG8 gdcbitreverse(REG8 data) {
+
+	REG8	ret;
+	UINT	cnt;
+
+	ret = 0;
+	cnt = 8;
+	do {
+		ret = (ret * 2) + (data & 1);
+		data >>= 1;
+	} while(--cnt);
+	return(ret);
+}
+#endif
 
 
-void gdcsub_init(void) {
+void gdcsub_initialize(void) {
 
 	int		i;
 
@@ -46,30 +105,112 @@ void gdcslavewait(NEVENTITEM item) {
 	}
 }
 
+void gdcsub_setslavewait(UINT32 wait) {
+
+	SINT32	clk;
+
+	clk = nevent_getremain(NEVENT_GDCSLAVE);
+	if (clk < 0) {
+		clk = 0;
+	}
+	gdc.s_drawing = 8;							// GDC DRAWING!
+	nevent_set(NEVENT_GDCSLAVE, clk + wait, gdcslavewait, NEVENT_ABSOLUTE);
+}
+
 static void calc_gdcslavewait(UINT dots) {
 
 	SINT32	clk;
 
 	clk = dots;
-	if (pccore.baseclock != PCBASECLOCK20) {
-		clk *= 27648;
+	if (pccore.cpumode & CPUMODE_8MHZ) {
+		clk *= 22464;
 	}
 	else {
-		clk *= 22464;
+		clk *= 27648;
 	}
 	clk *= pccore.multiple;
 	clk /= 15625;
 	clk += 30 * pccore.multiple;
-	gdc.s_drawing = 8;							// GDC DRAWING!
-	nevent_set(NEVENT_GDCSLAVE, clk, gdcslavewait, NEVENT_ABSOLUTE);
+	gdcsub_setslavewait(clk);
 }
 
-void gdcsub_line(UINT32 csrw, const GDCVECT *vect, UINT16 pat, BYTE ope) {
+void gdcsub_setvectl(GDCVECT *vect, int x1, int y1, int x2, int y2) {
+
+	UINT	ope;
+	int		dy;
+	int		dx;
+	int		tmp;
+
+	ope = 0;
+	dy = y2 - y1;
+	if (dy < 0) {
+		dy = 0 - dy;
+	}
+	dx = x2 - x1;
+	if (dx == 0) {
+		if (y1 <= y2) {
+			ope = 7;
+		}
+		else {
+			ope = 3;
+		}
+	}
+	else {
+		if (dx > 0) {
+			if (y1 >= y2) {
+				ope += 2;
+			}
+		}
+		else {
+			dx = 0 - dx;
+			ope += 4;
+			if (y1 <= y2) {
+				ope += 2;
+			}
+		}
+		if (ope & 2) {
+			if (dx <= dy) {
+				ope += 1;
+			}
+		}
+		else {
+			if (dx >= dy) {
+				ope += 1;
+			}
+		}
+	}
+	if (!((ope + 1) & 2)) {
+		tmp = dx;
+		dx = dy;
+		dy = tmp;
+	}
+	vect->ope = (UINT8)(ope + 0x08);
+	STOREINTELWORD(vect->DC, (UINT16)dx);
+	dy = dy * 2;
+	STOREINTELWORD(vect->D1, (UINT16)dy);
+	dy -= dx;
+	STOREINTELWORD(vect->D, (UINT16)dy);
+	dy -= dx;
+	STOREINTELWORD(vect->D2, (UINT16)dy);
+}
+
+
+// ----
+
+void gdcsub_vect0(UINT32 csrw, const GDCVECT *vect, REG16 pat, REG8 ope) {
+
+	(void)csrw;
+	(void)vect;
+	(void)pat;
+	(void)ope;
+}
+
+void gdcsub_vectl(UINT32 csrw, const GDCVECT *vect, REG16 pat, REG8 ope) {
 
 	_GDCPSET	pset;
 	UINT		dc;
-	UINT16		x;
-	UINT16		y;
+	REG16		x;
+	REG16		y;
 	UINT		i;
 	UINT16		step;
 	UINT		d1;
@@ -87,56 +228,56 @@ void gdcsub_line(UINT32 csrw, const GDCV
 			case 0:
 				for (i=0; i<=dc; i++) {
 					step = (UINT16)((((d1 * i) / dc) + 1) >> 1);
-					gdcpset(&pset, (UINT16)(x + step), y++);
+					gdcpset(&pset, (REG16)(x + step), y++);
 				}
 				break;
 
 			case 1:
 				for (i=0; i<=dc; i++) {
 					step = (UINT16)((((d1 * i) / dc) + 1) >> 1);
-					gdcpset(&pset, x++, (UINT16)(y + step));
+					gdcpset(&pset, x++, (REG16)(y + step));
 				}
 				break;
 
 			case 2:
 				for (i=0; i<=dc; i++) {
 					step = (UINT16)((((d1 * i) / dc) + 1) >> 1);
-					gdcpset(&pset, x++, (UINT16)(y - step));
+					gdcpset(&pset, x++, (REG16)(y - step));
 				}
 				break;
 
 			case 3:
 				for (i=0; i<=dc; i++) {
 					step = (UINT16)((((d1 * i) / dc) + 1) >> 1);
-					gdcpset(&pset, (UINT16)(x + step), y--);
+					gdcpset(&pset, (REG16)(x + step), y--);
 				}
 				break;
 
 			case 4:
 				for (i=0; i<=dc; i++) {
 					step = (UINT16)((((d1 * i) / dc) + 1) >> 1);
-					gdcpset(&pset, (UINT16)(x - step), y--);
+					gdcpset(&pset, (REG16)(x - step), y--);
 				}
 				break;
 
 			case 5:
 				for (i=0; i<=dc; i++) {
 					step = (UINT16)((((d1 * i) / dc) + 1) >> 1);
-					gdcpset(&pset, x--, (UINT16)(y - step));
+					gdcpset(&pset, x--, (REG16)(y - step));
 				}
 				break;
 
 			case 6:
 				for (i=0; i<=dc; i++) {
 					step = (UINT16)((((d1 * i) / dc) + 1) >> 1);
-					gdcpset(&pset, x--, (UINT16)(y + step));
+					gdcpset(&pset, x--, (REG16)(y + step));
 				}
 				break;
 
 			case 7:
 				for (i=0; i<=dc; i++) {
 					step = (UINT16)((((d1 * i) / dc) + 1) >> 1);
-					gdcpset(&pset, (UINT16)(x - step), y++);
+					gdcpset(&pset, (REG16)(x - step), y++);
 				}
 				break;
 		}
@@ -144,86 +285,62 @@ void gdcsub_line(UINT32 csrw, const GDCV
 	calc_gdcslavewait(pset.dots);
 }
 
-void gdcsub_box(UINT32 csrw, const GDCVECT *vect, UINT16 pat, BYTE ope) {
+void gdcsub_vectt(UINT32 csrw, const GDCVECT *vect, REG16 pat, REG8 ope) {
 
 	_GDCPSET	pset;
-	UINT		d;
-	UINT		d2;
-	UINT16		x;
-	UINT16		y;
-	UINT		i;
-
-	gdcpset_prepare(&pset, csrw, pat, ope);
-	d = (LOADINTELWORD(vect->D)) & 0x3fff;
-	d2 = (LOADINTELWORD(vect->D2)) & 0x3fff;
-	x = pset.x;
-	y = pset.y;
-	// 回転はなしよ(手抜き)
-	switch((vect->ope) & 7) {
-		case 0:
-			for (i=0; i<d; i++) {
-				gdcpset(&pset, x, y++);
-			}
-			for (i=0; i<d2; i++) {
-				gdcpset(&pset, x++, y);
-			}
-			for (i=0; i<d; i++) {
-				gdcpset(&pset, x, y--);
-			}
-			for (i=0; i<d2; i++) {
-				gdcpset(&pset, x--, y);
-			}
-			break;
-
-		case 2:
-			for (i=0; i<d; i++) {
-				gdcpset(&pset, x++, y);
-			}
-			for (i=0; i<d2; i++) {
-				gdcpset(&pset, x, y--);
-			}
-			for (i=0; i<d; i++) {
-				gdcpset(&pset, x--, y);
-			}
-			for (i=0; i<d2; i++) {
-				gdcpset(&pset, x, y++);
-			}
-			break;
+	BYTE		multiple;
+	UINT		sx;
+const VECTDIR	*dir;
+	BYTE		muly;
+	REG16		cx;
+	REG16		cy;
+	UINT		xrem;
+	BYTE		mulx;
 
-		case 4:
-			for (i=0; i<d; i++) {
-				gdcpset(&pset, x, y--);
-			}
-			for (i=0; i<d2; i++) {
-				gdcpset(&pset, x--, y);
-			}
-			for (i=0; i<d; i++) {
-				gdcpset(&pset, x, y++);
-			}
-			for (i=0; i<d2; i++) {
-				gdcpset(&pset, x++, y);
-			}
-			break;
+	if (vect->ope & 0x80) {		// SL
+		pat = (REG16)((GDCPATREVERSE(pat) << 8) + GDCPATREVERSE(pat >> 8));
+	}
+	gdcpset_prepare(&pset, csrw, 0xffff, ope);
+	multiple = (gdc.s.para[GDC_ZOOM] & 15) + 1;
 
-		case 6:
-			for (i=0; i<d; i++) {
-				gdcpset(&pset, x--, y);
-			}
-			for (i=0; i<d2; i++) {
-				gdcpset(&pset, x, y++);
-			}
-			for (i=0; i<d; i++) {
-				gdcpset(&pset, x++, y);
-			}
-			for (i=0; i<d2; i++) {
-				gdcpset(&pset, x, y--);
+	sx = LOADINTELWORD(vect->D);
+	sx = ((sx - 1) & 0x3fff) + 1;
+	if (sx >= 768) {
+		sx = 768;
+	}
+	dir = vectdir + ((vect->ope) & 7);
+
+	muly = multiple;
+	while(muly--) {
+		cx = pset.x;
+		cy = pset.y;
+		xrem = sx;
+		while(xrem--) {
+			mulx = multiple;
+			if (pat & 1) {
+				pat >>= 1;
+				pat |= 0x8000;
+				while(mulx--) {
+					gdcpset(&pset, cx, cy);
+					cx += dir->x;
+					cy += dir->y;
+				}
+			}
+			else {
+				pat >>= 1;
+				while(mulx--) {
+					cx += dir->x;
+					cy += dir->y;
+				}
 			}
-			break;
+		}
+		pset.x += dir->x2;
+		pset.y += dir->y2;
 	}
 	calc_gdcslavewait(pset.dots);
 }
 
-void gdcsub_circle(UINT32 csrw, const GDCVECT *vect, UINT16 pat, BYTE ope) {
+void gdcsub_vectc(UINT32 csrw, const GDCVECT *vect, REG16 pat, REG8 ope) {
 
 	_GDCPSET	pset;
 	UINT		r;
@@ -253,7 +370,7 @@ void gdcsub_circle(UINT32 csrw, const GD
 				for (; i<=t; i++) {
 					s = (gdc_rt[(i << RT_TABLEBIT) / m] * r);
 					s = (s + (1 << (RT_MULBIT - 1))) >> RT_MULBIT;
-					gdcpset(&pset, (UINT16)(x + s), (UINT16)(y + i));
+					gdcpset(&pset, (REG16)(x + s), (REG16)(y + i));
 				}
 				break;
 
@@ -261,7 +378,7 @@ void gdcsub_circle(UINT32 csrw, const GD
 				for (; i<=t; i++) {
 					s = (gdc_rt[(i << RT_TABLEBIT) / m] * r);
 					s = (s + (1 << (RT_MULBIT - 1))) >> RT_MULBIT;
-					gdcpset(&pset, (UINT16)(x + i), (UINT16)(y + s));
+					gdcpset(&pset, (REG16)(x + i), (REG16)(y + s));
 				}
 				break;
 
@@ -269,7 +386,7 @@ void gdcsub_circle(UINT32 csrw, const GD
 				for (; i<=t; i++) {
 					s = (gdc_rt[(i << RT_TABLEBIT) / m] * r);
 					s = (s + (1 << (RT_MULBIT - 1))) >> RT_MULBIT;
-					gdcpset(&pset, (UINT16)(x + i), (UINT16)(y - s));
+					gdcpset(&pset, (REG16)(x + i), (REG16)(y - s));
 				}
 				break;
 
@@ -277,7 +394,7 @@ void gdcsub_circle(UINT32 csrw, const GD
 				for (; i<=t; i++) {
 					s = (gdc_rt[(i << RT_TABLEBIT) / m] * r);
 					s = (s + (1 << (RT_MULBIT - 1))) >> RT_MULBIT;
-					gdcpset(&pset, (UINT16)(x + s), (UINT16)(y - i));
+					gdcpset(&pset, (REG16)(x + s), (REG16)(y - i));
 				}
 				break;
 
@@ -285,7 +402,7 @@ void gdcsub_circle(UINT32 csrw, const GD
 				for (; i<=t; i++) {
 					s = (gdc_rt[(i << RT_TABLEBIT) / m] * r);
 					s = (s + (1 << (RT_MULBIT - 1))) >> RT_MULBIT;
-					gdcpset(&pset, (UINT16)(x - s), (UINT16)(y - i));
+					gdcpset(&pset, (REG16)(x - s), (REG16)(y - i));
 				}
 				break;
 
@@ -293,7 +410,7 @@ void gdcsub_circle(UINT32 csrw, const GD
 				for (; i<=t; i++) {
 					s = (gdc_rt[(i << RT_TABLEBIT) / m] * r);
 					s = (s + (1 << (RT_MULBIT - 1))) >> RT_MULBIT;
-					gdcpset(&pset, (UINT16)(x - i), (UINT16)(y - s));
+					gdcpset(&pset, (REG16)(x - i), (REG16)(y - s));
 				}
 				break;
 
@@ -301,7 +418,7 @@ void gdcsub_circle(UINT32 csrw, const GD
 				for (; i<=t; i++) {
 					s = (gdc_rt[(i << RT_TABLEBIT) / m] * r);
 					s = (s + (1 << (RT_MULBIT - 1))) >> RT_MULBIT;
-					gdcpset(&pset, (UINT16)(x - i), (UINT16)(y + s));
+					gdcpset(&pset, (REG16)(x - i), (REG16)(y + s));
 				}
 				break;
 
@@ -309,7 +426,7 @@ void gdcsub_circle(UINT32 csrw, const GD
 				for (; i<=t; i++) {
 					s = (gdc_rt[(i << RT_TABLEBIT) / m] * r);
 					s = (s + (1 << (RT_MULBIT - 1))) >> RT_MULBIT;
-					gdcpset(&pset, (UINT16)(x - s), (UINT16)(y + i));
+					gdcpset(&pset, (REG16)(x - s), (REG16)(y + i));
 				}
 				break;
 		}
@@ -317,31 +434,81 @@ void gdcsub_circle(UINT32 csrw, const GD
 	calc_gdcslavewait(pset.dots);
 }
 
-void gdcsub_text(UINT32 csrw, const GDCVECT *vect, UINT16 pat, BYTE ope) {
+void gdcsub_vectr(UINT32 csrw, const GDCVECT *vect, REG16 pat, REG8 ope) {
+
+	_GDCPSET	pset;
+	UINT		d;
+	UINT		d2;
+	REG16		x;
+	REG16		y;
+	UINT		i;
+const VECTDIR	*dir;
+
+	gdcpset_prepare(&pset, csrw, pat, ope);
+	d = (LOADINTELWORD(vect->D)) & 0x3fff;
+	d2 = (LOADINTELWORD(vect->D2)) & 0x3fff;
+	x = pset.x;
+	y = pset.y;
+	dir = vectdir + ((vect->ope) & 7);
+	for (i=0; i<d; i++) {
+		gdcpset(&pset, x, y);
+		x += dir->x;
+		y += dir->y;
+	}
+	for (i=0; i<d2; i++) {
+		gdcpset(&pset, x, y);
+		x += dir->x2;
+		y += dir->y2;
+	}
+	for (i=0; i<d; i++) {
+		gdcpset(&pset, x, y);
+		x -= dir->x;
+		y -= dir->y;
+	}
+	for (i=0; i<d2; i++) {
+		gdcpset(&pset, x, y);
+		x -= dir->x2;
+		y -= dir->y2;
+	}
+	calc_gdcslavewait(pset.dots);
+}
+
+void gdcsub_text(UINT32 csrw, const GDCVECT *vect, const BYTE *pat,
+																REG8 ope) {
 
 	_GDCPSET	pset;
 	BYTE		multiple;
 	UINT		sx;
 	UINT		sy;
-const TEXTDIR	*dir;
+const VECTDIR	*dir;
 	UINT		patnum;
 	BYTE		muly;
-	UINT16		cx;
-	UINT16		cy;
+	REG16		cx;
+	REG16		cy;
 	UINT		xrem;
 	BYTE		bit;
 	BYTE		mulx;
 
-	gdcpset_prepare(&pset, csrw, pat, ope);
+	gdcpset_prepare(&pset, csrw, 0xffff, ope);
 	multiple = (gdc.s.para[GDC_ZOOM] & 15) + 1;
-#if 0
-	sx = (LOADINTELWORD(vect->DC)) & 0x3fff) + 1;
-	sy = (LOADINTELWORD(vect->D)) & 0x3fff) + 1;
+#if 1
+	sy = LOADINTELWORD(vect->DC);
+	sy = (sy & 0x3fff) + 1;
+	sx = LOADINTELWORD(vect->D);
+	sx = ((sx - 1) & 0x3fff) + 1;
+
+	// てきとーにリミット
+	if (sx >= 768) {
+		sx = 768;
+	}
+	if (sy >= 768) {
+		sy = 768;
+	}
 #else
 	sx = 8;
 	sy = 8;
 #endif
-	dir = textdir + ((vect->ope) & 7);
+	dir = vectdir + (((vect->ope & 0x80) >> 4) + ((vect->ope) & 7));
 	patnum = 0;
 
 	while(sy--) {
@@ -350,7 +517,7 @@ const TEXTDIR	*dir;
 		while(muly--) {
 			cx = pset.x;
 			cy = pset.y;
-			bit = gdc.s.para[GDC_TEXTW + (patnum & 7)];
+			bit = pat[patnum & 7];
 			xrem = sx;
 			while(xrem--) {
 				mulx = multiple;
@@ -371,8 +538,8 @@ const TEXTDIR	*dir;
 					}
 				}
 			}
-			pset.x += dir->sx;
-			pset.y += dir->sy;
+			pset.x += dir->x2;
+			pset.y += dir->y2;
 		}
 	}
 	calc_gdcslavewait(pset.dots);
@@ -456,7 +623,7 @@ void gdcsub_write(void) {
 	}
 	gdcs.grphdisp |= (BYTE)updatebit;
 
-	ptr += vramplaneseg[(adrs >> 14) & 3];
+	ptr += gdcplaneseg[(adrs >> 14) & 3];
 	adrs = (adrs & 0x3fff) << 1;
 	calc_gdcslavewait(leng);