Use values/cells/blocks format for short form

2 files changed, 88 insertions, 50 deletions

diff --git a/vespajlib/src/main/java/com/yahoo/tensor/serialization/JsonFormat.java b/vespajlib/src/main/java/com/yahoo/tensor/serialization/JsonFormat.java
index bebd706f815..87157495485 100644
--- a/vespajlib/src/main/java/com/yahoo/tensor/serialization/JsonFormat.java
+++ b/vespajlib/src/main/java/com/yahoo/tensor/serialization/JsonFormat.java
@@ -16,9 +16,11 @@ import com.yahoo.tensor.MixedTensor;
 import com.yahoo.tensor.Tensor;
 import com.yahoo.tensor.TensorAddress;
 import com.yahoo.tensor.TensorType;
+import com.yahoo.tensor.evaluation.Name;
 import com.yahoo.tensor.functions.ConstantTensor;
 import com.yahoo.tensor.functions.Slice;
 
+import java.util.ArrayList;
 import java.util.HashSet;
 import java.util.Iterator;
 import java.util.List;
@@ -61,23 +63,23 @@ public class JsonFormat {
         // Encode as nested lists if indexed tensor
         if (tensor instanceof IndexedTensor) {
             IndexedTensor denseTensor = (IndexedTensor) tensor;
-            encodeList(denseTensor, root.setArray("value"), new long[denseTensor.dimensionSizes().dimensions()], 0);
+            encodeValues(denseTensor, root.setArray("values"), new long[denseTensor.dimensionSizes().dimensions()], 0);
         }
 
         // Short form for a single mapped dimension
         else if (tensor instanceof MappedTensor && tensor.type().dimensions().size() == 1) {
-            encodeMap((MappedTensor) tensor, root.setObject("value"));
+            encodeSingleDimensionCells((MappedTensor) tensor, root);
         }
 
-        // Short form for a mixed tensor with a single mapped dimension
+        // Short form for a mixed tensor
         else if (tensor instanceof MixedTensor &&
-                tensor.type().dimensions().stream().filter(TensorType.Dimension::isMapped).count() == 1) {
-            encodeMapBlocks((MixedTensor) tensor, root.setObject("value"));
+                tensor.type().dimensions().stream().filter(TensorType.Dimension::isMapped).count() >= 1) {
+            encodeBlocks((MixedTensor) tensor, root);
         }
 
         // No other short forms exist: default to standard cell address output
         else {
-            encodeCells(tensor, root.setObject("value"));
+            encodeCells(tensor, root);
         }
 
         return com.yahoo.slime.JsonFormat.toJsonBytes(slime);
@@ -93,47 +95,76 @@ public class JsonFormat {
         }
     }
 
+    private static void encodeSingleDimensionCells(MappedTensor tensor, Cursor cursor) {
+        Cursor cells = cursor.setObject("cells");
+        if (tensor.type().dimensions().size() > 1)
+            throw new IllegalStateException("JSON encode of mapped tensor can only contain a single dimension");
+        tensor.cells().forEach((k,v) -> cells.setDouble(k.label(0), v));
+    }
+
     private static void encodeAddress(TensorType type, TensorAddress address, Cursor addressObject) {
         for (int i = 0; i < address.size(); i++)
             addressObject.setString(type.dimensions().get(i).name(), address.label(i));
     }
 
-    private static void encodeList(IndexedTensor tensor, Cursor cursor, long[] indexes, int dimension) {
+    private static void encodeValues(IndexedTensor tensor, Cursor cursor, long[] indexes, int dimension) {
         DimensionSizes sizes = tensor.dimensionSizes();
         for (indexes[dimension] = 0; indexes[dimension] < sizes.size(dimension); ++indexes[dimension]) {
             if (dimension < (sizes.dimensions() - 1)) {
-                encodeList(tensor, cursor.addArray(), indexes, dimension + 1);
+                encodeValues(tensor, cursor.addArray(), indexes, dimension + 1);
             } else {
                 cursor.addDouble(tensor.get(indexes));
             }
         }
     }
 
-    private static void encodeMap(MappedTensor tensor, Cursor cursor) {
-        if (tensor.type().dimensions().size() > 1)
-            throw new IllegalStateException("JSON encode of mapped tensor can only contain a single dimension");
-        tensor.cells().forEach((k,v) -> cursor.setDouble(k.label(0), v));
-    }
-
-    private static void encodeMapBlocks(MixedTensor tensor, Cursor cursor) {
-        var mappedDimensions = tensor.type().dimensions().stream().filter(d -> !d.isIndexed()).collect(Collectors.toList());
-        if (mappedDimensions.size() != 1) {
+    private static void encodeBlocks(MixedTensor tensor, Cursor cursor) {
+        var mappedDimensions = tensor.type().dimensions().stream().filter(d -> d.isMapped())
+                .map(d -> TensorType.Dimension.mapped(d.name())).collect(Collectors.toList());
+        if (mappedDimensions.size() < 1) {
             throw new IllegalArgumentException("Should be ensured by caller");
         }
-        String mappedDimensionName = mappedDimensions.get(0).name();
-        int mappedDimensionIndex = tensor.type().indexOfDimension(mappedDimensionName).
-                orElseThrow(() -> new IllegalStateException("Could not find mapped dimension index"));
+        cursor = (mappedDimensions.size() == 1) ? cursor.setObject("blocks") : cursor.setArray("blocks");
 
-        // Find all unique indices for the mapped dimension
-        Set<String> mappedIndices = new HashSet<>();
-        tensor.cellIterator().forEachRemaining((cell) -> mappedIndices.add(cell.getKey().label(mappedDimensionIndex)));
+        // Create tensor type for mapped dimensions subtype
+        TensorType mappedSubType = new TensorType.Builder(mappedDimensions).build();
+
+        // Find all unique indices for the mapped dimensions
+        Set<TensorAddress> denseSubSpaceAddresses = new HashSet<>();
+        tensor.cellIterator().forEachRemaining((cell) -> {
+            denseSubSpaceAddresses.add(subAddress(cell.getKey(), mappedSubType, tensor.type()));
+        });
 
         // Slice out dense subspace of each and encode dense subspace as a list
-        for (String mappedIndex : mappedIndices) {
-            IndexedTensor denseSubspace = (IndexedTensor) new Slice<>(new ConstantTensor<>(tensor),
-                    List.of(new Slice.DimensionValue<>(mappedDimensionName, mappedIndex))).evaluate();
-            encodeList(denseSubspace, cursor.setArray(mappedIndex), new long[denseSubspace.dimensionSizes().dimensions()], 0);
+        for (TensorAddress denseSubSpaceAddress : denseSubSpaceAddresses) {
+            IndexedTensor denseSubspace = (IndexedTensor) sliceSubAddress(tensor, denseSubSpaceAddress, mappedSubType);
+
+            if (mappedDimensions.size() == 1) {
+                encodeValues(denseSubspace, cursor.setArray(denseSubSpaceAddress.label(0)), new long[denseSubspace.dimensionSizes().dimensions()], 0);
+            } else {
+                Cursor block = cursor.addObject();
+                encodeAddress(mappedSubType, denseSubSpaceAddress, block.setObject("address"));
+                encodeValues(denseSubspace, block.setArray("values"), new long[denseSubspace.dimensionSizes().dimensions()], 0);
+            }
+
+        }
+    }
+
+    private static TensorAddress subAddress(TensorAddress address, TensorType subType, TensorType origType) {
+        TensorAddress.Builder builder = new TensorAddress.Builder(subType);
+        for (TensorType.Dimension dim : subType.dimensions()) {
+            builder.add(dim.name(), address.label(origType.indexOfDimension(dim.name()).
+                    orElseThrow(() -> new IllegalStateException("Could not find mapped dimension index"))));
+        }
+        return builder.build();
+    }
+
+    private static Tensor sliceSubAddress(Tensor tensor, TensorAddress subAddress, TensorType subType) {
+        List<Slice.DimensionValue<Name>> sliceDims = new ArrayList<>(subAddress.size());
+        for (int i = 0; i < subAddress.size(); ++i) {
+            sliceDims.add(new Slice.DimensionValue<>(subType.dimensions().get(i).name(), subAddress.label(i)));
         }
+        return new Slice<>(new ConstantTensor<>(tensor), sliceDims).evaluate();
     }
 
     /** Deserializes the given tensor from JSON format */
diff --git a/vespajlib/src/test/java/com/yahoo/tensor/serialization/JsonFormatTestCase.java b/vespajlib/src/test/java/com/yahoo/tensor/serialization/JsonFormatTestCase.java
index 15017dc95ca..cdfd19eb5c8 100644
--- a/vespajlib/src/test/java/com/yahoo/tensor/serialization/JsonFormatTestCase.java
+++ b/vespajlib/src/test/java/com/yahoo/tensor/serialization/JsonFormatTestCase.java
@@ -98,55 +98,62 @@ public class JsonFormatTestCase {
     }
 
     @Test
-    public void testDenseTensorShortForm() {
+    public void testEncodeIndexedShortForm() {
         assertEncodeShortForm("tensor(x[]):[1.0, 2.0]",
-                              "{\"type\":\"tensor(x[])\",\"value\":[1.0,2.0]}");
+                              "{\"type\":\"tensor(x[])\",\"values\":[1.0,2.0]}");
         assertEncodeShortForm("tensor<float>(x[]):[1.0, 2.0]",
-                              "{\"type\":\"tensor<float>(x[])\",\"value\":[1.0,2.0]}");
+                              "{\"type\":\"tensor<float>(x[])\",\"values\":[1.0,2.0]}");
         assertEncodeShortForm("tensor(x[],y[]):[[1,2,3,4]]",
-                              "{\"type\":\"tensor(x[],y[])\",\"value\":[[1.0,2.0,3.0,4.0]]}");
+                              "{\"type\":\"tensor(x[],y[])\",\"values\":[[1.0,2.0,3.0,4.0]]}");
         assertEncodeShortForm("tensor(x[],y[]):[[1,2],[3,4]]",
-                              "{\"type\":\"tensor(x[],y[])\",\"value\":[[1.0,2.0],[3.0,4.0]]}");
+                              "{\"type\":\"tensor(x[],y[])\",\"values\":[[1.0,2.0],[3.0,4.0]]}");
         assertEncodeShortForm("tensor(x[],y[]):[[1],[2],[3],[4]]",
-                              "{\"type\":\"tensor(x[],y[])\",\"value\":[[1.0],[2.0],[3.0],[4.0]]}");
+                              "{\"type\":\"tensor(x[],y[])\",\"values\":[[1.0],[2.0],[3.0],[4.0]]}");
         assertEncodeShortForm("tensor(x[],y[],z[]):[[[1,2],[3,4]]]",
-                              "{\"type\":\"tensor(x[],y[],z[])\",\"value\":[[[1.0,2.0],[3.0,4.0]]]}");
+                              "{\"type\":\"tensor(x[],y[],z[])\",\"values\":[[[1.0,2.0],[3.0,4.0]]]}");
         assertEncodeShortForm("tensor(x[],y[],z[]):[[[1],[2],[3],[4]]]",
-                              "{\"type\":\"tensor(x[],y[],z[])\",\"value\":[[[1.0],[2.0],[3.0],[4.0]]]}");
+                              "{\"type\":\"tensor(x[],y[],z[])\",\"values\":[[[1.0],[2.0],[3.0],[4.0]]]}");
         assertEncodeShortForm("tensor(x[],y[],z[]):[[[1,2,3,4]]]",
-                              "{\"type\":\"tensor(x[],y[],z[])\",\"value\":[[[1.0,2.0,3.0,4.0]]]}");
+                              "{\"type\":\"tensor(x[],y[],z[])\",\"values\":[[[1.0,2.0,3.0,4.0]]]}");
         assertEncodeShortForm("tensor(x[],y[],z[]):[[[1]],[[2]],[[3]],[[4]]]",
-                              "{\"type\":\"tensor(x[],y[],z[])\",\"value\":[[[1.0]],[[2.0]],[[3.0]],[[4.0]]]}");
+                              "{\"type\":\"tensor(x[],y[],z[])\",\"values\":[[[1.0]],[[2.0]],[[3.0]],[[4.0]]]}");
         assertEncodeShortForm("tensor(x[],y[],z[2]):[[[1, 2]],[[3, 4]]]",
-                              "{\"type\":\"tensor(x[],y[],z[2])\",\"value\":[[[1.0,2.0]],[[3.0,4.0]]]}");
+                              "{\"type\":\"tensor(x[],y[],z[2])\",\"values\":[[[1.0,2.0]],[[3.0,4.0]]]}");
     }
 
     @Test
-    public void testSingleDimensionSparseTensorShortForm() {
-        assertEncodeShortForm("tensor(x{}):{a:1, b:2}",
-                              "{\"type\":\"tensor(x{})\",\"value\":{\"a\":1.0,\"b\":2.0}}");
-
+    public void testEncodeMappedSingleDimensionShortForm() {
+        assertEncodeShortForm("tensor(x{}):{}",
+                              "{\"type\":\"tensor(x{})\",\"cells\":{}}");
+        assertEncodeShortForm("tensor(x{}):{a:1,b:2}",
+                              "{\"type\":\"tensor(x{})\",\"cells\":{\"a\":1.0,\"b\":2.0}}");
         // Multiple mapped dimensions: no short form available
         assertEncodeShortForm("tensor(x{},y{}):{{x:a,y:b}:1,{x:c,y:d}:2}",
-                              "{\"type\":\"tensor(x{},y{})\",\"value\":{\"cells\":[{\"address\":{\"x\":\"a\",\"y\":\"b\"},\"value\":1.0},{\"address\":{\"x\":\"c\",\"y\":\"d\"},\"value\":2.0}]}}");
+                              "{\"type\":\"tensor(x{},y{})\",\"cells\":[{\"address\":{\"x\":\"a\",\"y\":\"b\"},\"value\":1.0},{\"address\":{\"x\":\"c\",\"y\":\"d\"},\"value\":2.0}]}");
     }
 
     @Test
-    public void testSingleMappedDimensionMixedTensorShortForm() {
+    public void testEncodeMixedShortForm() {
         assertEncodeShortForm("tensor(x{},y[2]):{a:[1,2], b:[3,4] }",
-                              "{\"type\":\"tensor(x{},y[2])\",\"value\":{\"a\":[1.0,2.0],\"b\":[3.0,4.0]}}");
+                              "{\"type\":\"tensor(x{},y[2])\",\"blocks\":{\"a\":[1.0,2.0],\"b\":[3.0,4.0]}}");
         assertEncodeShortForm("tensor(x[2],y{}):{a:[1,2], b:[3,4] }",
-                              "{\"type\":\"tensor(x[2],y{})\",\"value\":{\"a\":[1.0,2.0],\"b\":[3.0,4.0]}}");
+                              "{\"type\":\"tensor(x[2],y{})\",\"blocks\":{\"a\":[1.0,2.0],\"b\":[3.0,4.0]}}");
         assertEncodeShortForm("tensor(x{},y[2],z[2]):{a:[[1,2],[3,4]], b:[[5,6],[7,8]] }",
-                              "{\"type\":\"tensor(x{},y[2],z[2])\",\"value\":{\"a\":[[1.0,2.0],[3.0,4.0]],\"b\":[[5.0,6.0],[7.0,8.0]]}}");
+                              "{\"type\":\"tensor(x{},y[2],z[2])\",\"blocks\":{\"a\":[[1.0,2.0],[3.0,4.0]],\"b\":[[5.0,6.0],[7.0,8.0]]}}");
         assertEncodeShortForm("tensor(x[1],y{},z[4]):{a:[[1,2,3,4]], b:[[5,6,7,8]] }",
-                              "{\"type\":\"tensor(x[1],y{},z[4])\",\"value\":{\"a\":[[1.0,2.0,3.0,4.0]],\"b\":[[5.0,6.0,7.0,8.0]]}}");
+                              "{\"type\":\"tensor(x[1],y{},z[4])\",\"blocks\":{\"a\":[[1.0,2.0,3.0,4.0]],\"b\":[[5.0,6.0,7.0,8.0]]}}");
         assertEncodeShortForm("tensor(x[4],y[1],z{}):{a:[[1],[2],[3],[4]], b:[[5],[6],[7],[8]] }",
-                              "{\"type\":\"tensor(x[4],y[1],z{})\",\"value\":{\"a\":[[1.0],[2.0],[3.0],[4.0]],\"b\":[[5.0],[6.0],[7.0],[8.0]]}}");
+                              "{\"type\":\"tensor(x[4],y[1],z{})\",\"blocks\":{\"a\":[[1.0],[2.0],[3.0],[4.0]],\"b\":[[5.0],[6.0],[7.0],[8.0]]}}");
         assertEncodeShortForm("tensor(a[2],b[2],c{},d[2]):{a:[[[1,2], [3,4]], [[5,6], [7,8]]], b:[[[1,2], [3,4]], [[5,6], [7,8]]] }",
-                              "{\"type\":\"tensor(a[2],b[2],c{},d[2])\",\"value\":{" +
+                              "{\"type\":\"tensor(a[2],b[2],c{},d[2])\",\"blocks\":{" +
                                     "\"a\":[[[1.0,2.0],[3.0,4.0]],[[5.0,6.0],[7.0,8.0]]]," +
                                     "\"b\":[[[1.0,2.0],[3.0,4.0]],[[5.0,6.0],[7.0,8.0]]]}}");
+
+        // Multiple mapped dimensions
+        assertEncodeShortForm("tensor(x{},y{},z[2]):{{x:a,y:0,z:0}:1, {x:a,y:0,z:1}:2, {x:b,y:1,z:0}:3, {x:b,y:1,z:1}:4 }",
+                              "{\"type\":\"tensor(x{},y{},z[2])\",\"blocks\":[{\"address\":{\"x\":\"a\",\"y\":\"0\"},\"values\":[1.0,2.0]},{\"address\":{\"x\":\"b\",\"y\":\"1\"},\"values\":[3.0,4.0]}]}");
+        assertEncodeShortForm("tensor(x{},y[2],z{}):{{x:a,y:0,z:0}:1, {x:a,y:1,z:0}:2, {x:b,y:0,z:1}:3, {x:b,y:1,z:1}:4 }",
+                              "{\"type\":\"tensor(x{},y[2],z{})\",\"blocks\":[{\"address\":{\"x\":\"a\",\"z\":\"0\"},\"values\":[1.0,2.0]},{\"address\":{\"x\":\"b\",\"z\":\"1\"},\"values\":[3.0,4.0]}]}");
     }
 
     @Test