libv4l: add sn9c20x-i420 decoder

From: Vasily Khoruzhick <anarsoul@gmail.com>

Recent sn9c20x driver written by microdia project
(http://groups.goolge.com/group/microdia) introduce new output format -
sn9c20x-i420. This format is actually scrambled yuv420, so it's very easy and
fast to convert it to yuv420. This patch adds sn9c20x-i420 decoder to the
libv4l-0.5.7

This decoder is much faster than jpeg one (sn9c20x supports JPEG too):
sn9c20x-i420 decoder eats only 10% of 1GHz CPU at 640x480x25fps vs 40% of
1GHz CPU in jpeg at same frame size/rate.

This format should be preffered for sn9c20x, because sn9c20x driver supports
SBGGR8 too, so it should go before SBGGR8 in supported_src_pixfmts.

Priority: normal

Signed-off-by: Vasily Khoruzhick <anarsoul@gmail.com>
Signed-off-by: Hans de Goede <hdegoede@redhat.com

5 files changed, 153 insertions, 2 deletions

diff --git a/v4l2-apps/libv4l/ChangeLog b/v4l2-apps/libv4l/ChangeLog
index a23632027..3a97a1893 100644
--- a/v4l2-apps/libv4l/ChangeLog
+++ b/v4l2-apps/libv4l/ChangeLog
@@ -8,6 +8,8 @@ libv4l-0.5.8
 * Switch to using USB-id's instead of USB product string, as not all devices
   set a unique product string. This fixes the upside down issues with
   genius e-messenger 112 cams
+* Add support for sn9c20x-i420 format patch by Vasily Khoruzhick
+  <anarsoul@gmail.com>
 
 libv4l-0.5.7
 ------------
diff --git a/v4l2-apps/libv4l/libv4lconvert/Makefile b/v4l2-apps/libv4l/libv4lconvert/Makefile
index fa0f3f5e0..22c512cd5 100644
--- a/v4l2-apps/libv4l/libv4lconvert/Makefile
+++ b/v4l2-apps/libv4l/libv4lconvert/Makefile
@@ -10,7 +10,7 @@ CONVERT_LIB   = libv4lconvert.so
 override CPPFLAGS += -fPIC
 endif
 
-CONVERT_OBJS  = libv4lconvert.o tinyjpeg.o sn9c10x.o pac207.o flip.o crop.o \
+CONVERT_OBJS  = libv4lconvert.o tinyjpeg.o sn9c10x.o sn9c20x.o pac207.o flip.o crop.o \
 		jidctflt.o spca561-decompress.o rgbyuv.o spca501.o bayer.o
 TARGETS       = $(CONVERT_LIB) libv4lconvert.pc
 INCLUDES      = ../include/libv4lconvert.h
diff --git a/v4l2-apps/libv4l/libv4lconvert/libv4lconvert-priv.h b/v4l2-apps/libv4l/libv4lconvert/libv4lconvert-priv.h
index 6bcf2cb26..08a7a7cfa 100644
--- a/v4l2-apps/libv4l/libv4lconvert/libv4lconvert-priv.h
+++ b/v4l2-apps/libv4l/libv4lconvert/libv4lconvert-priv.h
@@ -63,6 +63,10 @@
 #define V4L2_PIX_FMT_YVYU v4l2_fourcc('Y', 'V', 'Y', 'U')
 #endif
 
+#ifndef V4L2_PIX_FMT_SN9C20X_I420
+#define V4L2_PIX_FMT_SN9C20X_I420  v4l2_fourcc('S', '9', '2', '0')
+#endif
+
 #define V4LCONVERT_ERROR_MSG_SIZE 256
 #define V4LCONVERT_MAX_FRAMESIZES 16
 
@@ -157,6 +161,9 @@ void v4lconvert_spca505_to_yuv420(const unsigned char *src, unsigned char *dst,
 void v4lconvert_spca508_to_yuv420(const unsigned char *src, unsigned char *dst,
   int width, int height, int yvu);
 
+void v4lconvert_sn9c20x_to_yuv420(const unsigned char *src, unsigned char *dst,
+  int width, int height, int yvu);
+
 void v4lconvert_decode_spca561(const unsigned char *src, unsigned char *dst,
   int width, int height);
 
diff --git a/v4l2-apps/libv4l/libv4lconvert/libv4lconvert.c b/v4l2-apps/libv4l/libv4lconvert/libv4lconvert.c
index 8cc63d47a..43c25ec94 100644
--- a/v4l2-apps/libv4l/libv4lconvert/libv4lconvert.c
+++ b/v4l2-apps/libv4l/libv4lconvert/libv4lconvert.c
@@ -47,6 +47,7 @@ static const struct v4lconvert_pixfmt supported_src_pixfmts[] = {
   { V4L2_PIX_FMT_YUYV,    0 },
   { V4L2_PIX_FMT_YVYU,    0 },
   { V4L2_PIX_FMT_UYVY,    0 },
+  { V4L2_PIX_FMT_SN9C20X_I420, 0 },
   { V4L2_PIX_FMT_SBGGR8,  0 },
   { V4L2_PIX_FMT_SGBRG8,  0 },
   { V4L2_PIX_FMT_SGRBG8,  0 },
@@ -572,10 +573,11 @@ static int v4lconvert_convert_pixfmt(struct v4lconvert_data *data,
       }
       break;
 
-    /* YUYV line by line formats */
+    /* Custom cam specific YUV formats */
     case V4L2_PIX_FMT_SPCA501:
     case V4L2_PIX_FMT_SPCA505:
     case V4L2_PIX_FMT_SPCA508:
+    case V4L2_PIX_FMT_SN9C20X_I420:
     {
       unsigned char *d;
       int yvu = 0;
@@ -602,6 +604,9 @@ static int v4lconvert_convert_pixfmt(struct v4lconvert_data *data,
 	case V4L2_PIX_FMT_SPCA508:
 	  v4lconvert_spca508_to_yuv420(src, d, width, height, yvu);
 	  break;
+	case V4L2_PIX_FMT_SN9C20X_I420:
+	  v4lconvert_sn9c20x_to_yuv420(src, d, width, height, yvu);
+	  break;
       }
 
       switch (dest_pix_fmt) {
diff --git a/v4l2-apps/libv4l/libv4lconvert/sn9c20x.c b/v4l2-apps/libv4l/libv4lconvert/sn9c20x.c
new file mode 100644
index 000000000..19951300f
--- /dev/null
+++ b/v4l2-apps/libv4l/libv4lconvert/sn9c20x.c
@@ -0,0 +1,137 @@
+/*
+ * Sonix SN9C20X decoder
+ * Vasily Khoruzhick, (C) 2008-2009
+ * Algorithm based on Java code written by Jens on microdia google group
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU Lesser General Public License as published by
+ * the Free Software Foundation; either version 2.1 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU Lesser General Public License for more details.
+ *
+ * You should have received a copy of the GNU Lesser General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ *
+ * Note this code was originally licensed under the GNU GPL instead of the
+ * GNU LGPL, its license has been changed by its author.
+ */
+
+#include "libv4lconvert-priv.h"
+
+#define DO_SANITY_CHECKS 0
+
+static const int UVTranslate[32] = {0, 1, 2, 3,
+			8, 9, 10, 11,
+			16, 17, 18, 19,
+			24, 25, 26, 27,
+			4, 5, 6, 7,
+			12, 13, 14, 15,
+			20, 21, 22, 23,
+			28, 29, 30, 31};
+
+static const int Y_coords_624x[128][2] = {
+{ 0,  0}, { 1,  0}, { 2,  0}, { 3,  0}, { 4,  0}, { 5,  0}, { 6,  0}, { 7,  0},
+{ 0,  1}, { 1,  1}, { 2,  1}, { 3,  1}, { 4,  1}, { 5,  1}, { 6,  1}, { 7,  1},
+{ 0,  2}, { 1,  2}, { 2,  2}, { 3,  2}, { 4,  2}, { 5,  2}, { 6,  2}, { 7,  2},
+{ 0,  3}, { 1,  3}, { 2,  3}, { 3,  3}, { 4,  3}, { 5,  3}, { 6,  3}, { 7,  3},
+
+{ 0,  4}, { 1,  4}, { 2,  4}, { 3,  4}, { 4,  4}, { 5,  4}, { 6,  4}, { 7,  4},
+{ 0,  5}, { 1,  5}, { 2,  5}, { 3,  5}, { 4,  5}, { 5,  5}, { 6,  5}, { 7,  5},
+{ 0,  6}, { 1,  6}, { 2,  6}, { 3,  6}, { 4,  6}, { 5,  6}, { 6,  6}, { 7,  6},
+{ 0,  7}, { 1,  7}, { 2,  7}, { 3,  7}, { 4,  7}, { 5,  7}, { 6,  7}, { 7,  7},
+
+{ 8,  0}, { 9,  0}, {10,  0}, {11,  0}, {12,  0}, {13,  0}, {14,  0}, {15,  0},
+{ 8,  1}, { 9,  1}, {10,  1}, {11,  1}, {12,  1}, {13,  1}, {14,  1}, {15,  1},
+{ 8,  2}, { 9,  2}, {10,  2}, {11,  2}, {12,  2}, {13,  2}, {14,  2}, {15,  2},
+{ 8,  3}, { 9,  3}, {10,  3}, {11,  3}, {12,  3}, {13,  3}, {14,  3}, {15,  3},
+
+{ 8,  4}, { 9,  4}, {10,  4}, {11,  4}, {12,  4}, {13,  4}, {14,  4}, {15,  4},
+{ 8,  5}, { 9,  5}, {10,  5}, {11,  5}, {12,  5}, {13,  5}, {14,  5}, {15,  5},
+{ 8,  6}, { 9,  6}, {10,  6}, {11,  6}, {12,  6}, {13,  6}, {14,  6}, {15,  6},
+{ 8,  7}, { 9,  7}, {10,  7}, {11,  7}, {12,  7}, {13,  7}, {14,  7}, {15,  7}
+};
+
+static void do_write_u(const unsigned char *buf, unsigned char *ptr,
+	int i, int j)
+{
+	*ptr = buf[i + 128 + j];
+}
+
+static void do_write_v(const unsigned char *buf, unsigned char *ptr,
+	int i, int j)
+{
+	*ptr = buf[i + 160 + j];
+}
+
+void v4lconvert_sn9c20x_to_yuv420(const unsigned char *raw, unsigned char *i420,
+  int width, int height, int yvu)
+{
+	int i = 0, x = 0, y = 0, j, relX, relY, x_div2, y_div2;
+	const unsigned char *buf = raw;
+	unsigned char *ptr;
+	int frame_size = width * height;
+	int frame_size_div2 = frame_size >> 1;
+	int frame_size_div4 = frame_size >> 2;
+	int width_div2 = width >> 1;
+	int height_div2 = height >> 1;
+	void (*do_write_uv1)(const unsigned char *buf, unsigned char *ptr, int i,
+	int j) = NULL;
+	void (*do_write_uv2)(const unsigned char *buf, unsigned char *ptr, int i,
+	int j) = NULL;
+
+	if (yvu) {
+		do_write_uv1 = do_write_v;
+		do_write_uv2 = do_write_u;
+	}
+	else {
+		do_write_uv1 = do_write_u;
+		do_write_uv2 = do_write_v;
+	}
+
+	while (i < (frame_size + frame_size_div2)) {
+		for (j = 0; j < 128; j++) {
+			relX = x + Y_coords_624x[j][0];
+			relY = y + Y_coords_624x[j][1];
+
+#if (DO_SANITY_CHECKS==1)
+			if ((relX < width) && (relY < height)) {
+#endif
+				ptr = i420 + relY * width + relX;
+				*ptr = buf[i + j];
+#if (DO_SANITY_CHECKS==1)
+			}
+#endif
+
+		}
+		x_div2 = x >> 1;
+		y_div2 = y >> 1;
+		for (j = 0; j < 32; j++) {
+			relX = (x_div2) + (j & 0x07);
+			relY = (y_div2) + (j >> 3);
+
+#if (DO_SANITY_CHECKS==1)
+			if ((relX < width_div2) && (relY < height_div2)) {
+#endif
+				ptr = i420 + frame_size +
+					relY * width_div2 + relX;
+				do_write_uv1(buf, ptr, i, j);
+				ptr += frame_size_div4;
+				do_write_uv2(buf, ptr, i, j);
+#if (DO_SANITY_CHECKS==1)
+			}
+#endif
+		}
+
+		i += 192;
+		x += 16;
+		if (x >= width) {
+			x = 0;
+			y += 8;
+		}
+	}
+}