Merge remote-tracking branch 'qatar/master'

* qatar/master: (21 commits)
  swscale: Add Doxygen for hyscale_fast/hScale.
  fate: enable lavfi-pixmt tests on big endian systems
  PPC: swscale: disable altivec functions for unsupported formats
  fate: merge identical pixdesc_be/le tests
  swscale: Add Doxygen for yuv2planar*/yuv2packed* functions.
  build: call texi2pod.pl with full path instead of symlink
  build: include sub-makefiles using full path instead of symlinks
  swscale: update big endian reference values after dff5a835.
  wavpack: skip blocks with no samples
  cosmetics: remove outdated comment that is no longer true
  build: replace some addprefix/addsuffix with substitution refs
  avutil: Remove unused arbitrary precision integer code.
  configure: Drop check for availability of ten assembler operands.
  aacenc: Save channel configuration for later use.
  aacenc: Fix codebook trellising for zeroed bands.
  swscale: change prototypes of scaled YUV output functions.
  swscale: re-add support for non-native endianness.
  swscale: disentangle yuv2rgbX_c_full() into small functions.
  swscale: split yuv2packed[12X]_c() remainders into small functions.
  swscale: split yuv2packedX_altivec in smaller functions.
  ...

Conflicts:
	Makefile
	configure
	libavcodec/x86/dsputil_mmx.c
	libavfilter/Makefile
	libavformat/Makefile
	libavutil/integer.c
	libavutil/integer.h
	libswscale/swscale.c
	libswscale/swscale_internal.h
	libswscale/x86/swscale_template.c
	tests/ref/lavfi/pixdesc_le
	tests/ref/lavfi/pixfmts_scale

Merged-by: Michael Niedermayer <michaelni@gmx.at>

1 files changed, 159 insertions, 25 deletions

diff --git a/libswscale/swscale_internal.h b/libswscale/swscale_internal.h
index 27de6b24d0..84c3b1c575 100644
--- a/libswscale/swscale_internal.h
+++ b/libswscale/swscale_internal.h
@@ -59,40 +59,129 @@ typedef int (*SwsFunc)(struct SwsContext *context, const uint8_t* src[],
                        int srcStride[], int srcSliceY, int srcSliceH,
                        uint8_t* dst[], int dstStride[]);
 
+/**
+ * Write one line of horizontally scaled Y/U/V/A to planar output
+ * without any additional vertical scaling (or point-scaling).
+ *
+ * @param c       SWS scaling context
+ * @param lumSrc  scaled luma (Y) source data, 15bit for 8bit output
+ * @param chrUSrc scaled chroma (U) source data, 15bit for 8bit output
+ * @param chrVSrc scaled chroma (V) source data, 15bit for 8bit output
+ * @param alpSrc  scaled alpha (A) source data, 15bit for 8bit output
+ * @param dest    pointer to the 4 output planes (Y/U/V/A)
+ * @param dstW    width of dest[0], dest[3], lumSrc and alpSrc in pixels
+ * @param chrDstW width of dest[1], dest[2], chrUSrc and chrVSrc
+ */
 typedef void (*yuv2planar1_fn) (struct SwsContext *c,
                                 const int16_t *lumSrc, const int16_t *chrUSrc,
                                 const int16_t *chrVSrc, const int16_t *alpSrc,
-                                uint8_t *dest,
-                                uint8_t *uDest, uint8_t *vDest, uint8_t *aDest,
-                                int dstW, int chrDstW, const uint8_t *lumDither, const uint8_t *chrDither);
-typedef void (*yuv2planarX_fn) (struct SwsContext *c,
-                                const int16_t *lumFilter, const int16_t **lumSrc, int lumFilterSize,
+                                uint8_t *dest[4], int dstW, int chrDstW,
+                                const uint8_t *lumDither, const uint8_t *chrDither);
+/**
+ * Write one line of horizontally scaled Y/U/V/A to planar output
+ * with multi-point vertical scaling between input pixels.
+ *
+ * @param c             SWS scaling context
+ * @param lumFilter     vertical luma/alpha scaling coefficients, 12bit [0,4096]
+ * @param lumSrc        scaled luma (Y) source data, 15bit for 8bit output
+ * @param lumFilterSize number of vertical luma/alpha input lines to scale
+ * @param chrFilter     vertical chroma scaling coefficients, 12bit [0,4096]
+ * @param chrUSrc       scaled chroma (U) source data, 15bit for 8bit output
+ * @param chrVSrc       scaled chroma (V) source data, 15bit for 8bit output
+ * @param chrFilterSize number of vertical chroma input lines to scale
+ * @param alpSrc        scaled alpha (A) source data, 15bit for 8bit output
+ * @param dest          pointer to the 4 output planes (Y/U/V/A)
+ * @param dstW          width of dest[0], dest[3], lumSrc and alpSrc in pixels
+ * @param chrDstW       width of dest[1], dest[2], chrUSrc and chrVSrc
+ */
+typedef void (*yuv2planarX_fn) (struct SwsContext *c, const int16_t *lumFilter,
+                                const int16_t **lumSrc, int lumFilterSize,
                                 const int16_t *chrFilter, const int16_t **chrUSrc,
-                                const int16_t **chrVSrc, int chrFilterSize,
-                                const int16_t **alpSrc,
-                                uint8_t *dest,
-                                uint8_t *uDest, uint8_t *vDest, uint8_t *aDest,
+                                const int16_t **chrVSrc,  int chrFilterSize,
+                                const int16_t **alpSrc, uint8_t *dest[4],
                                 int dstW, int chrDstW, const uint8_t *lumDither, const uint8_t *chrDither);
-typedef void (*yuv2packed1_fn) (struct SwsContext *c,
-                                const uint16_t *buf0,
-                                const uint16_t *ubuf0, const uint16_t *ubuf1,
-                                const uint16_t *vbuf0, const uint16_t *vbuf1,
-                                const uint16_t *abuf0,
-                                uint8_t *dest,
-                                int dstW, int uvalpha, int dstFormat, int flags, int y);
-typedef void (*yuv2packed2_fn) (struct SwsContext *c,
-                                const uint16_t *buf0, const uint16_t *buf1,
-                                const uint16_t *ubuf0, const uint16_t *ubuf1,
-                                const uint16_t *vbuf0, const uint16_t *vbuf1,
-                                const uint16_t *abuf0, const uint16_t *abuf1,
-                                uint8_t *dest,
+/**
+ * Write one line of horizontally scaled Y/U/V/A to packed-pixel YUV/RGB
+ * output without any additional vertical scaling (or point-scaling). Note
+ * that this function may do chroma scaling, see the "uvalpha" argument.
+ *
+ * @param c       SWS scaling context
+ * @param lumSrc  scaled luma (Y) source data, 15bit for 8bit output
+ * @param chrUSrc scaled chroma (U) source data, 15bit for 8bit output
+ * @param chrVSrc scaled chroma (V) source data, 15bit for 8bit output
+ * @param alpSrc  scaled alpha (A) source data, 15bit for 8bit output
+ * @param dest    pointer to the output plane
+ * @param dstW    width of lumSrc and alpSrc in pixels, number of pixels
+ *                to write into dest[]
+ * @param uvalpha chroma scaling coefficient for the second line of chroma
+ *                pixels, either 2048 or 0. If 0, one chroma input is used
+ *                for 2 output pixels (or if the SWS_FLAG_FULL_CHR_INT flag
+ *                is set, it generates 1 output pixel). If 2048, two chroma
+ *                input pixels should be averaged for 2 output pixels (this
+ *                only happens if SWS_FLAG_FULL_CHR_INT is not set)
+ * @param y       vertical line number for this output. This does not need
+ *                to be used to calculate the offset in the destination,
+ *                but can be used to generate comfort noise using dithering
+ *                for some output formats.
+ */
+typedef void (*yuv2packed1_fn) (struct SwsContext *c,  const int16_t *lumSrc,
+                                const int16_t *chrUSrc[2], const int16_t *chrVSrc[2],
+                                const int16_t *alpSrc,  uint8_t *dest,
+                                int dstW, int uvalpha, int y);
+/**
+ * Write one line of horizontally scaled Y/U/V/A to packed-pixel YUV/RGB
+ * output by doing bilinear scaling between two input lines.
+ *
+ * @param c       SWS scaling context
+ * @param lumSrc  scaled luma (Y) source data, 15bit for 8bit output
+ * @param chrUSrc scaled chroma (U) source data, 15bit for 8bit output
+ * @param chrVSrc scaled chroma (V) source data, 15bit for 8bit output
+ * @param alpSrc  scaled alpha (A) source data, 15bit for 8bit output
+ * @param dest    pointer to the output plane
+ * @param dstW    width of lumSrc and alpSrc in pixels, number of pixels
+ *                to write into dest[]
+ * @param yalpha  luma/alpha scaling coefficients for the second input line.
+ *                The first line's coefficients can be calculated by using
+ *                4096 - yalpha
+ * @param uvalpha chroma scaling coefficient for the second input line. The
+ *                first line's coefficients can be calculated by using
+ *                4096 - uvalpha
+ * @param y       vertical line number for this output. This does not need
+ *                to be used to calculate the offset in the destination,
+ *                but can be used to generate comfort noise using dithering
+ *                for some output formats.
+ */
+typedef void (*yuv2packed2_fn) (struct SwsContext *c,  const int16_t *lumSrc[2],
+                                const int16_t *chrUSrc[2], const int16_t *chrVSrc[2],
+                                const int16_t *alpSrc[2], uint8_t *dest,
                                 int dstW, int yalpha, int uvalpha, int y);
-typedef void (*yuv2packedX_fn) (struct SwsContext *c,
-                                const int16_t *lumFilter, const int16_t **lumSrc, int lumFilterSize,
+/**
+ * Write one line of horizontally scaled Y/U/V/A to packed-pixel YUV/RGB
+ * output by doing multi-point vertical scaling between input pixels.
+ *
+ * @param c             SWS scaling context
+ * @param lumFilter     vertical luma/alpha scaling coefficients, 12bit [0,4096]
+ * @param lumSrc        scaled luma (Y) source data, 15bit for 8bit output
+ * @param lumFilterSize number of vertical luma/alpha input lines to scale
+ * @param chrFilter     vertical chroma scaling coefficients, 12bit [0,4096]
+ * @param chrUSrc       scaled chroma (U) source data, 15bit for 8bit output
+ * @param chrVSrc       scaled chroma (V) source data, 15bit for 8bit output
+ * @param chrFilterSize number of vertical chroma input lines to scale
+ * @param alpSrc        scaled alpha (A) source data, 15bit for 8bit output
+ * @param dest          pointer to the output plane
+ * @param dstW          width of lumSrc and alpSrc in pixels, number of pixels
+ *                      to write into dest[]
+ * @param y             vertical line number for this output. This does not need
+ *                      to be used to calculate the offset in the destination,
+ *                      but can be used to generate comfort noise using dithering
+ *                      or some output formats.
+ */
+typedef void (*yuv2packedX_fn) (struct SwsContext *c, const int16_t *lumFilter,
+                                const int16_t **lumSrc, int lumFilterSize,
                                 const int16_t *chrFilter, const int16_t **chrUSrc,
                                 const int16_t **chrVSrc, int chrFilterSize,
                                 const int16_t **alpSrc, uint8_t *dest,
-                                int dstW, int dstY);
+                                int dstW, int y);
 
 /* This struct should be aligned on at least a 32-byte boundary. */
 typedef struct SwsContext {
@@ -304,6 +393,25 @@ typedef struct SwsContext {
     void (*chrToYV12)(uint8_t *dstU, uint8_t *dstV,
                       const uint8_t *src1, const uint8_t *src2,
                       int width, uint32_t *pal); ///< Unscaled conversion of chroma planes to YV12 for horizontal scaler.
+    /**
+     * Scale one horizontal line of input data using a bilinear filter
+     * to produce one line of output data. Compared to SwsContext->hScale(),
+     * please take note of the following caveats when using these:
+     * - Scaling is done using only 7bit instead of 14bit coefficients.
+     * - You can use no more than 5 input pixels to produce 4 output
+     *   pixels. Therefore, this filter should not be used for downscaling
+     *   by more than ~20% in width (because that equals more than 5/4th
+     *   downscaling and thus more than 5 pixels input per 4 pixels output).
+     * - In general, bilinear filters create artifacts during downscaling
+     *   (even when <20%), because one output pixel will span more than one
+     *   input pixel, and thus some pixels will need edges of both neighbor
+     *   pixels to interpolate the output pixel. Since you can use at most
+     *   two input pixels per output pixel in bilinear scaling, this is
+     *   impossible and thus downscaling by any size will create artifacts.
+     * To enable this type of scaling, set SWS_FLAG_FAST_BILINEAR
+     * in SwsContext->flags.
+     */
+    /** @{ */
     void (*hyscale_fast)(struct SwsContext *c,
                          int16_t *dst, int dstWidth,
                          const uint8_t *src, int srcW, int xInc);
@@ -311,7 +419,33 @@ typedef struct SwsContext {
                          int16_t *dst1, int16_t *dst2, int dstWidth,
                          const uint8_t *src1, const uint8_t *src2,
                          int srcW, int xInc);
+    /** @} */
 
+    /**
+     * Scale one horizontal line of input data using a filter over the input
+     * lines, to produce one (differently sized) line of output data.
+     *
+     * @param dst        pointer to destination buffer for horizontally scaled
+     *                   data. If the scaling depth (SwsContext->scalingBpp) is
+     *                   8, data will be 15bpp in 16bits (int16_t) width. If
+     *                   scaling depth is 16, data will be 19bpp in 32bpp
+     *                   (int32_t) width.
+     * @param dstW       width of destination image
+     * @param src        pointer to source data to be scaled. If scaling depth
+     *                   is 8, this is 8bpp in 8bpp (uint8_t) width. If scaling
+     *                   depth is 16, this is 16bpp in 16bpp (uint16_t) depth.
+     * @param filter     filter coefficients to be used per output pixel for
+     *                   scaling. This contains 14bpp filtering coefficients.
+     *                   Guaranteed to contain dstW * filterSize entries.
+     * @param filterPos  position of the first input pixel to be used for
+     *                   each output pixel during scaling. Guaranteed to
+     *                   contain dstW entries.
+     * @param filterSize the number of input coefficients to be used (and
+     *                   thus the number of input pixels to be used) for
+     *                   creating a single output pixel. Is aligned to 4
+     *                   (and input coefficients thus padded with zeroes)
+     *                   to simplify creating SIMD code.
+     */
     void (*hScale)(int16_t *dst, int dstW, const uint8_t *src,
                    const int16_t *filter, const int16_t *filterPos,
                    int filterSize);