enable obtaining the unsorted dimensions list

... as a side-effect of parsing a type spec

5 files changed, 59 insertions, 3 deletions

diff --git a/eval/src/tests/eval/value_type/value_type_test.cpp b/eval/src/tests/eval/value_type/value_type_test.cpp
index 42b34c0d3ea..d0b48759578 100644
--- a/eval/src/tests/eval/value_type/value_type_test.cpp
+++ b/eval/src/tests/eval/value_type/value_type_test.cpp
@@ -162,6 +162,37 @@ TEST("require that value type spec can be parsed with extra whitespace") {
     EXPECT_EQUAL(ValueType::tensor_type({{"y", 10}}, CellType::FLOAT), ValueType::from_spec(" tensor < float > ( y [ 10 ] ) "));
 }
 
+TEST("require that the unsorted dimension list can be obtained when parsing type spec") {
+    std::vector<ValueType::Dimension> unsorted;
+    auto type = ValueType::from_spec("tensor(y[10],z[5],x{})", unsorted);
+    EXPECT_EQUAL(ValueType::tensor_type({{"x"}, {"y", 10}, {"z", 5}}), type);
+    ASSERT_EQUAL(unsorted.size(), 3u);
+    EXPECT_EQUAL(unsorted[0].name, "y");
+    EXPECT_EQUAL(unsorted[0].size, 10u);
+    EXPECT_EQUAL(unsorted[1].name, "z");
+    EXPECT_EQUAL(unsorted[1].size, 5u);
+    EXPECT_EQUAL(unsorted[2].name, "x");
+    EXPECT_EQUAL(unsorted[2].size, npos);
+}
+
+TEST("require that the unsorted dimension list can be obtained also when the type spec is invalid") {
+    std::vector<ValueType::Dimension> unsorted;
+    auto type = ValueType::from_spec("tensor(x[10],x[5])...", unsorted);
+    EXPECT_TRUE(type.is_error());
+    ASSERT_EQUAL(unsorted.size(), 2u);
+    EXPECT_EQUAL(unsorted[0].name, "x");
+    EXPECT_EQUAL(unsorted[0].size, 10u);
+    EXPECT_EQUAL(unsorted[1].name, "x");
+    EXPECT_EQUAL(unsorted[1].size, 5u);
+}
+
+TEST("require that the unsorted dimension list can not be obtained if the parse itself fails") {
+    std::vector<ValueType::Dimension> unsorted;
+    auto type = ValueType::from_spec("tensor(x[10],x[5]", unsorted);
+    EXPECT_TRUE(type.is_error());
+    EXPECT_EQUAL(unsorted.size(), 0u);
+}
+
 TEST("require that malformed value type spec is parsed as error") {
     EXPECT_TRUE(ValueType::from_spec("").is_error());
     EXPECT_TRUE(ValueType::from_spec("  ").is_error());
diff --git a/eval/src/vespa/eval/eval/value_type.cpp b/eval/src/vespa/eval/eval/value_type.cpp
index 688112bbb8a..211a9c305a3 100644
--- a/eval/src/vespa/eval/eval/value_type.cpp
+++ b/eval/src/vespa/eval/eval/value_type.cpp
@@ -260,6 +260,12 @@ ValueType::from_spec(const vespalib::string &spec)
     return value_type::from_spec(spec);
 }
 
+ValueType
+ValueType::from_spec(const vespalib::string &spec, std::vector<ValueType::Dimension> &unsorted)
+{
+    return value_type::from_spec(spec, unsorted);
+}
+
 vespalib::string
 ValueType::to_spec() const
 {
diff --git a/eval/src/vespa/eval/eval/value_type.h b/eval/src/vespa/eval/eval/value_type.h
index df9c582aee8..b02053be3cb 100644
--- a/eval/src/vespa/eval/eval/value_type.h
+++ b/eval/src/vespa/eval/eval/value_type.h
@@ -77,6 +77,7 @@ public:
     static ValueType double_type() { return ValueType(Type::DOUBLE); }
     static ValueType tensor_type(std::vector<Dimension> dimensions_in, CellType cell_type = CellType::DOUBLE);
     static ValueType from_spec(const vespalib::string &spec);
+    static ValueType from_spec(const vespalib::string &spec, std::vector<ValueType::Dimension> &unsorted);
     vespalib::string to_spec() const;
     static ValueType join(const ValueType &lhs, const ValueType &rhs);
     static CellType unify_cell_types(const ValueType &a, const ValueType &b);
diff --git a/eval/src/vespa/eval/eval/value_type_spec.cpp b/eval/src/vespa/eval/eval/value_type_spec.cpp
index bbfa6f4fa28..0246800ca2a 100644
--- a/eval/src/vespa/eval/eval/value_type_spec.cpp
+++ b/eval/src/vespa/eval/eval/value_type_spec.cpp
@@ -176,7 +176,8 @@ CellType parse_cell_type(ParseContext &ctx) {
 } // namespace vespalib::eval::value_type::<anonymous>
 
 ValueType
-parse_spec(const char *pos_in, const char *end_in, const char *&pos_out)
+parse_spec(const char *pos_in, const char *end_in, const char *&pos_out,
+           std::vector<ValueType::Dimension> *unsorted)
 {
     ParseContext ctx(pos_in, end_in, pos_out);
     vespalib::string type_name = parse_ident(ctx);
@@ -188,6 +189,9 @@ parse_spec(const char *pos_in, const char *end_in, const char *&pos_out)
         ValueType::CellType cell_type = parse_cell_type(ctx);
         std::vector<ValueType::Dimension> list = parse_dimension_list(ctx);
         if (!ctx.failed()) {
+            if (unsorted != nullptr) {
+                *unsorted = list;
+            }
             return ValueType::tensor_type(std::move(list), cell_type);
         }
     } else {
@@ -208,6 +212,18 @@ from_spec(const vespalib::string &spec)
     return type;
 }
 
+ValueType
+from_spec(const vespalib::string &spec, std::vector<ValueType::Dimension> &unsorted)
+{
+    const char *after = nullptr;
+    const char *end = spec.data() + spec.size();
+    ValueType type = parse_spec(spec.data(), end, after, &unsorted);
+    if (after != end) {
+        return ValueType::error_type();
+    }
+    return type;
+}
+
 vespalib::string
 to_spec(const ValueType &type)
 {
diff --git a/eval/src/vespa/eval/eval/value_type_spec.h b/eval/src/vespa/eval/eval/value_type_spec.h
index f2609f59f32..ff5113c769a 100644
--- a/eval/src/vespa/eval/eval/value_type_spec.h
+++ b/eval/src/vespa/eval/eval/value_type_spec.h
@@ -6,9 +6,11 @@
 
 namespace vespalib::eval::value_type {
 
-ValueType parse_spec(const char *pos_in, const char *end_in, const char *&pos_out);
+ValueType parse_spec(const char *pos_in, const char *end_in, const char *&pos_out,
+                     std::vector<ValueType::Dimension> *unsorted = nullptr);
 
-ValueType from_spec(const vespalib::string &str);
+ValueType from_spec(const vespalib::string &spec);
+ValueType from_spec(const vespalib::string &spec, std::vector<ValueType::Dimension> &unsorted);
 vespalib::string to_spec(const ValueType &type);
 
 }