Add bgra (z,y,x) sampled transform lookup table api

Add an API to extract a color transform lookup table in BGRA format, with
(z,y,x) sampling order (B changes the slowest, R the fastest).

See r314425 for speed results, noting that qcms_chain_transform takes 8ms
for a 32-cube since floating-point is used to compute the color transform
to maintain transform precision.

The float data produced by qcms_chain_transform() is stored in the output
in BGRA order (color components are rounded to the nearest 8-bit integer)
with time cost 0.000031 secs. Note that if the data needed re-indexing to
(x,y,z) sampled, RGBA order on writing to the output, the time cost would
be 0.00056 secs (18 times slower) [1].

[1] See r314425 review comments about sampling and pixel order.

BUG=443863

Review URL: https://codereview.chromium.org/892413005

Cr-Commit-Position: refs/heads/master@{#315188}

3 files changed, 72 insertions, 1 deletions

diff --git a/third_party/qcms/README.chromium b/third_party/qcms/README.chromium
index 8fb3768..368d604 100644
--- a/third_party/qcms/README.chromium
+++ b/third_party/qcms/README.chromium
@@ -53,5 +53,7 @@ google.patch contains the following modifications. Apply with
    - https://code.google.com/p/chromium/issues/detail?id=401971
  - Avoid divisions creating sample points in the float cube LUT builder
    - https://code.google.com/p/chromium/issues/detail?id=443863
+ - Add bgra (z,y,x) sampled transform lookup table api
+   - https://code.google.com/p/chromium/issues/detail?id=443863
 To regenerate google.patch:
   git diff b8456f38 src > google.patch
diff --git a/third_party/qcms/src/qcms.h b/third_party/qcms/src/qcms.h
index c69a772..e9c0b09 100644
--- a/third_party/qcms/src/qcms.h
+++ b/third_party/qcms/src/qcms.h
@@ -158,11 +158,15 @@ qcms_transform* qcms_transform_create(
 		qcms_profile* out, qcms_data_type out_type,
 		qcms_intent intent);
 
-void qcms_transform_release(qcms_transform *);
+qcms_bool qcms_transform_create_LUT_zyx_bgra(
+		qcms_profile *in, qcms_profile* out, qcms_intent intent,
+		int samples, unsigned char* lut);
 
 void qcms_transform_data(qcms_transform *transform, void *src, void *dest, size_t length);
 void qcms_transform_data_type(qcms_transform *transform, void *src, void *dest, size_t length, qcms_output_type type);
 
+void qcms_transform_release(qcms_transform *);
+
 void qcms_enable_iccv4();
 
 #ifdef  __cplusplus
diff --git a/third_party/qcms/src/transform.c b/third_party/qcms/src/transform.c
index 9fd8238..f669a6b 100644
--- a/third_party/qcms/src/transform.c
+++ b/third_party/qcms/src/transform.c
@@ -1167,6 +1167,71 @@ qcms_transform* qcms_transform_precacheLUT_float(qcms_transform *transform, qcms
 	return transform;
 }
 
+/* Create a transform LUT using the given number of sample points. The transform LUT data is stored
+   in the output (cube) in bgra format in zyx sample order. */
+qcms_bool qcms_transform_create_LUT_zyx_bgra(qcms_profile *in, qcms_profile *out, qcms_intent intent,
+                                             int samples, unsigned char* cube)
+{
+	uint16_t z,y,x;
+	uint32_t l,index;
+	uint32_t lutSize = 3 * samples * samples * samples;
+
+	float* src = NULL;
+	float* dest = NULL;
+	float* lut = NULL;
+	float inverse;
+
+	src = malloc(lutSize*sizeof(float));
+	dest = malloc(lutSize*sizeof(float));
+
+	if (src && dest) {
+		/* Prepare a list of points we want to sample: z, y, x order */
+		l = 0;
+		inverse = 1 / (float)(samples-1);
+		for (z = 0; z < samples; z++) {
+			for (y = 0; y < samples; y++) {
+				for (x = 0; x < samples; x++) {
+					src[l++] = x * inverse; // r
+					src[l++] = y * inverse; // g
+					src[l++] = z * inverse; // b
+				}
+			}
+		}
+
+		lut = qcms_chain_transform(in, out, src, dest, lutSize);
+
+		if (lut) {
+			index = l = 0;
+			for (z = 0; z < samples; z++) {
+				for (y = 0; y < samples; y++) {
+					for (x = 0; x < samples; x++) {
+						cube[index++] = (int)floorf(lut[l + 2] * 255.0f + 0.5f); // b
+						cube[index++] = (int)floorf(lut[l + 1] * 255.0f + 0.5f); // g
+						cube[index++] = (int)floorf(lut[l + 0] * 255.0f + 0.5f); // r
+						cube[index++] = 255;                                     // a
+						l += 3;
+					}
+				}
+			}
+		}
+	}
+
+	// XXX: qcms_modular_transform_data may return the lut data in either the src or
+	// dest buffer so free src, dest, and lut with care.
+
+	if (src && lut != src)
+		free(src);
+	if (dest && lut != dest)
+		free(dest);
+
+	if (lut) {
+		free(lut);
+		return true;
+	}
+
+	return false;
+}
+
 #define NO_MEM_TRANSFORM NULL
 
 qcms_transform* qcms_transform_create(