Point to produced reference files

hahnjo · hahnjo · commit 663ec038698f · 2026-04-22T11:48:32.000+02:00
Closes #37
diff --git a/README.md b/README.md
@@ -4,7 +4,7 @@ The *RNTuple Validation Suite* provides conformance tests for the [RNTuple Binar
 The goal is to cover all parts of the specification with implications on the format.
 It can be used to validate both writer and reader implementations of the RNTuple specification.
 To that end, each test comes with a written description of the schema and the expected data.
-We also provide a set of reference `.root` and `.json` files (see below).
+Reference files for version 1.0.0 can be found under the [GitHub Release](https://github.com/root-project/rntuple-validation/releases/tag/v1.0.0).
 
 ## Test Categories
 
diff --git a/compression/README.md b/compression/README.md
@@ -2,7 +2,7 @@
 
 For the RNTuple Validation Suite, we assume that compression is orthogonal to the supported types and serialized data.
 Therefore all tests in this category write a single `Int64` field with type `std::int64_t` and column type `SplitInt64`.
-The entries have ascending values and the reference `.json` files only contain the sum of all elements.
+The entries have ascending values and the reference files (`compression.*.json`) only contain the sum of all elements.
 
  * [`algorithms`](algorithms): `zlib`, `lzma`, `lz4`, `zstd`
  * [`block`](block): big and short compression blocks
diff --git a/projections/cardinality/README.md b/projections/cardinality/README.md
@@ -11,3 +11,5 @@
 2. Empty vectors
 3. Increasing number of elements in the vector:
    one element in the first field, two elements in the second field, etc.
+
+The values can be found in the reference file `projections.cardinality.json`.
diff --git a/projections/collection/README.md b/projections/collection/README.md
@@ -9,3 +9,5 @@
 
 1. Ascending values
 2. Empty collection
+
+The values can be found in the reference file `projections.collection.json`.
diff --git a/projections/leaf/README.md b/projections/leaf/README.md
@@ -8,3 +8,5 @@
 ## Entries
 
 1. Ascending values
+
+The values can be found in the reference file `projections.leaf.json`.
diff --git a/projections/nested/README.md b/projections/nested/README.md
@@ -9,3 +9,5 @@
 
 1. Ascending values
 2. Empty collection
+
+The values can be found in the reference file `projections.nested.json`.
diff --git a/structure/README.md b/structure/README.md
@@ -2,6 +2,7 @@
 
 For the RNTuple Validation Suite, we assume that the structure is orthogonal to the supported types and serialized data.
 Therefore all tests in this category write a single `Int32` field with type `std::int32_t` the entries have ascending values.
+The values can be found in the reference files (`structure.*.json`).
 
  * [`clusters`](clusters): multiple clusters
  * [`cluster_groups`](cluster_groups): multiple cluster groups
diff --git a/structure/feature_flag/README.md b/structure/feature_flag/README.md
@@ -1,6 +1,6 @@
 # Unknown feature flag set
 
 An empty RNTuple with feature flag 137 (>62) set in the header. Reading should fail accordingly.
-The error message should indicate the feature flag.
+The error message should indicate the feature flag, as documented in the reference file `structure.feature_flag.json`.
 
 A later version of this test should set the flag in the footer.
diff --git a/types/RVec/fundamental/README.md b/types/RVec/fundamental/README.md
@@ -13,3 +13,5 @@ All child fields use the default column encoding `Int32`.
 2. Empty vectors
 3. Increasing number of elements in the vector:
    one element in the first field, two elements in the second field, etc.
+
+The values can be found in the reference file `types.RVec.fundamental.json`.
diff --git a/types/RVec/nested/README.md b/types/RVec/nested/README.md
@@ -12,3 +12,5 @@ All child fields use the default column encoding `Int32`.
 1. Single-element vectors, with ascending values
 2. Empty vectors
 3. Increasing number of elements in the outer vector, with arbitrary lengths of the inner vectors
+
+The values can be found in the reference file `types.RVec.nested.json`.
diff --git a/types/array/README.md b/types/array/README.md
@@ -14,3 +14,5 @@ with the default column types.
 
 1. Simple values
 2. Zero / empty values
+
+The values can be found in the reference file `types.array.json`.
diff --git a/types/atomic/README.md b/types/atomic/README.md
@@ -14,3 +14,5 @@ with the corresponding column types.
 
 1. Ascending values
 2. Zero values
+
+The values can be found in the reference file `types.atomic.json`.
diff --git a/types/bitset/README.md b/types/bitset/README.md
@@ -13,3 +13,5 @@ with the default column types.
 1. Ascending bits set
 2. All bits set
 3. All bits unset
+
+The values can be found in the reference file `types.bitset.json`.
diff --git a/types/fundamental/integer/README.md b/types/fundamental/integer/README.md
@@ -14,3 +14,5 @@ with the corresponding column types.
 3. Negative values for signed integer types (to validate zigzag encoding)
 4. Minimum (lowest) values
 5. Maximum values
+
+The values can be found in the reference file `types.fundamental.integer.json`.
diff --git a/types/fundamental/misc/README.md b/types/fundamental/misc/README.md
@@ -13,3 +13,5 @@ with the corresponding column types.
 1. Ascending values
 2. Low values
 3. High values
+
+The values can be found in the reference file `types.fundamental.misc.json`.
diff --git a/types/fundamental/real/README.md b/types/fundamental/real/README.md
@@ -19,3 +19,5 @@ with the corresponding field and column types.
 4. Smallest positive normal values
 5. Smallest positive subnormal values
 6. Maximum values
+
+The values can be found in the reference file `types.fundamental.real.json`.
diff --git a/types/fundamental/real32quant/README.md b/types/fundamental/real32quant/README.md
@@ -19,3 +19,5 @@ and a value range of `[-1, 1]` unless noted otherwise.
 3. Middle values of the fields' value range
 4. Min values of the fields' value range
 5. Max values of the fields' value range
+
+The values can be found in the reference file `types.fundamental.real32trunc.json`.
diff --git a/types/fundamental/real32trunc/README.md b/types/fundamental/real32trunc/README.md
@@ -19,3 +19,5 @@ with the corresponding field, column types and bit width.
 4. Smallest positive normal values with N bits
 5. Smallest positive subnormal values with N bits
 6. Maximum values with N bits
+
+The values can be found in the reference file `types.fundamental.real32quant.json`.
diff --git a/types/map/fundamental/README.md b/types/map/fundamental/README.md
@@ -13,3 +13,5 @@ All child fields use the default column types for `std::string` (`Index64` for t
 2. Empty maps
 3. Increasing number of elements in the map:
    one key-value pair in the first field, two key-value pairs in the second field, etc.
+
+The values can be found in the reference file `types.map.fundamental.json`.
diff --git a/types/map/nested/README.md b/types/map/nested/README.md
@@ -13,6 +13,8 @@ All child fields use the default column types for `std::string` (`Index64` for t
 2. Empty maps
 3. Increasing number of elements in the outer map, with arbitrary lengths of the inner maps
 
+The values can be found in the reference file `types.map.nested.json`.
+
 ## Dictionaries
 
 These tests require ROOT dictionaries, which can be generated with the provided `Makefile` in this directory. This will create a `libNestedMap` shared object.
diff --git a/types/multimap/fundamental/README.md b/types/multimap/fundamental/README.md
@@ -13,3 +13,5 @@ All child fields use the default column types for `std::string` (`Index64` for t
 2. Empty maps
 3. Increasing number of elements in the map:
    one key-value pair in the first field, two key-value pairs in the second field, etc.
+
+The values can be found in the reference file `types.multimap.fundamental.json`.
diff --git a/types/multimap/nested/README.md b/types/multimap/nested/README.md
@@ -13,6 +13,8 @@ All child fields use the default column types for `std::string` (`Index64` for t
 2. Empty maps
 3. Increasing number of elements in the outer map, with arbitrary lengths of the inner maps
 
+The values can be found in the reference file `types.multimap.nested.json`.
+
 ## Dictionaries
 
 These tests require ROOT dictionaries, which can be generated with the provided `Makefile` in this directory. This will create a `libNestedMultimap` shared object.
diff --git a/types/multiset/fundamental/README.md b/types/multiset/fundamental/README.md
@@ -13,3 +13,5 @@ All child fields use the default column encoding `Int32`.
 2. Empty sets
 3. Increasing number of elements in the set:
    one element in the first field, two elements in the second field, etc.
+
+The values can be found in the reference file `types.multiset.fundamental.json`.
diff --git a/types/multiset/nested/README.md b/types/multiset/nested/README.md
@@ -13,6 +13,8 @@ All child fields use the default column encoding `Int32`.
 2. Empty sets
 3. Increasing number of elements in the outer set, with arbitrary lengths of the inner sets
 
+The values can be found in the reference file `types.multiset.nested.json`.
+
 ## Dictionaries
 
 These tests require ROOT dictionaries, which can be generated with the provided `Makefile` in this directory. This will create a `libNestedMultiset` shared object.
diff --git a/types/optional/README.md b/types/optional/README.md
@@ -16,3 +16,5 @@ with otherwise the default column types.
 1. Simple values
 2. No value
 3. Zero / empty values
+
+The values can be found in the reference file `types.optional.json`.
diff --git a/types/pair/README.md b/types/pair/README.md
@@ -13,3 +13,5 @@ with the default column types.
 
 1. Simple values
 2. Zero / empty values
+
+The values can be found in the reference file `types.pair.json`.
diff --git a/types/set/fundamental/README.md b/types/set/fundamental/README.md
@@ -13,3 +13,5 @@ All child fields use the default column encoding `Int32`.
 2. Empty sets
 3. Increasing number of elements in the set:
    one element in the first field, two elements in the second field, etc.
+
+The values can be found in the reference file `types.set.fundamental.json`.
diff --git a/types/set/nested/README.md b/types/set/nested/README.md
@@ -13,6 +13,8 @@ All child fields use the default column encoding `Int32`.
 2. Empty sets
 3. Increasing number of elements in the outer set, with arbitrary lengths of the inner sets
 
+The values can be found in the reference file `types.set.nested.json`.
+
 ## Dictionaries
 
 These tests require ROOT dictionaries, which can be generated with the provided `Makefile` in this directory. This will create a `libNestedSet` shared object.
diff --git a/types/string/README.md b/types/string/README.md
@@ -13,3 +13,5 @@ with the corresponding column type for the first (principal) column.
 3. Unicode characters as UTF-8
 4. Increasing length of strings:
    one character in the first field, two characters in the second field, etc.
+
+The values can be found in the reference file `types.string.json`.
diff --git a/types/tuple/README.md b/types/tuple/README.md
@@ -13,3 +13,5 @@ with the default column types.
 
 1. Simple values
 2. Zero / empty values
+
+The values can be found in the reference file `types.tuple.json`.
diff --git a/types/unique_ptr/README.md b/types/unique_ptr/README.md
@@ -16,3 +16,5 @@ with otherwise the default column types.
 1. Simple values
 2. No value
 3. Zero / empty values
+
+The values can be found in the reference file `types.unique_ptr.json`.
diff --git a/types/unordered_map/fundamental/README.md b/types/unordered_map/fundamental/README.md
@@ -13,3 +13,5 @@ All child fields use the default column types for `std::string` (`Index64` for t
 2. Empty maps
 3. Increasing number of elements in the map:
    one key-value pair in the first field, two key-value pairs in the second field, etc.
+
+The values can be found in the reference file `types.unordered_map.fundamental.json`.
diff --git a/types/unordered_map/nested/README.md b/types/unordered_map/nested/README.md
@@ -13,6 +13,8 @@ All child fields use the default column types for `std::string` (`Index64` for t
 2. Empty maps
 3. Increasing number of elements in the outer map, with arbitrary lengths of the inner maps
 
+The values can be found in the reference file `types.unordered_map.nested.json`.
+
 ## Dictionaries
 
 These tests require ROOT dictionaries, which can be generated with the provided `Makefile` in this directory. This will create a `libNestedUnorderedMap` shared object.
diff --git a/types/unordered_multimap/fundamental/README.md b/types/unordered_multimap/fundamental/README.md
@@ -13,3 +13,5 @@ All child fields use the default column types for `std::string` (`Index64` for t
 2. Empty maps
 3. Increasing number of elements in the map:
    one key-value pair in the first field, two key-value pairs in the second field, etc.
+
+The values can be found in the reference file `types.unordered_multimap.fundamental.json`.
diff --git a/types/unordered_multimap/nested/README.md b/types/unordered_multimap/nested/README.md
@@ -13,6 +13,8 @@ All child fields use the default column types for `std::string` (`Index64` for t
 2. Empty maps
 3. Increasing number of elements in the outer map, with arbitrary lengths of the inner maps
 
+The values can be found in the reference file `types.unordered_multimap.nested.json`.
+
 ## Dictionaries
 
 These tests require ROOT dictionaries, which can be generated with the provided `Makefile` in this directory. This will create a `libNestedUnorderedMultimap` shared object.
diff --git a/types/unordered_multiset/fundamental/README.md b/types/unordered_multiset/fundamental/README.md
@@ -13,3 +13,5 @@ All child fields use the default column encoding `Int32`.
 2. Empty sets
 3. Increasing number of elements in the set:
    one element in the first field, two elements in the second field, etc.
+
+The values can be found in the reference file `types.unordered_multiset.fundamental.json`.
diff --git a/types/unordered_multiset/nested/README.md b/types/unordered_multiset/nested/README.md
@@ -13,6 +13,8 @@ All child fields use the default column encoding `Int32`.
 2. Empty sets
 3. Increasing number of elements in the outer set, with arbitrary lengths of the inner sets
 
+The values can be found in the reference file `types.unordered_multiset.nested.json`.
+
 ## Dictionaries
 
 These tests require ROOT dictionaries, which can be generated with the provided `Makefile` in this directory. This will create a `libNestedUnorderedMultiset` shared object.
diff --git a/types/unordered_set/fundamental/README.md b/types/unordered_set/fundamental/README.md
@@ -13,3 +13,5 @@ All child fields use the default column encoding `Int32`.
 2. Empty sets
 3. Increasing number of elements in the set:
    one element in the first field, two elements in the second field, etc.
+
+The values can be found in the reference file `types.unordered_set.fundamental.json`.
diff --git a/types/unordered_set/nested/README.md b/types/unordered_set/nested/README.md
@@ -13,6 +13,8 @@ All child fields use the default column encoding `Int32`.
 2. Empty sets
 3. Increasing number of elements in the outer set, with arbitrary lengths of the inner sets
 
+The values can be found in the reference file `types.unordered_set.nested.json`.
+
 ## Dictionaries
 
 These tests require ROOT dictionaries, which can be generated with the provided `Makefile` in this directory. This will create a `libNestedUnorderedSet` shared object.
diff --git a/types/user/class/README.md b/types/user/class/README.md
@@ -18,3 +18,5 @@ with the default column types.
 
 1. Simple values
 2. Zero / empty values
+
+The values can be found in the reference file `types.user.class.json`.
diff --git a/types/user/enum/README.md b/types/user/enum/README.md
@@ -10,3 +10,5 @@ with the default column types.
 
 1. Simple values
 2. Zero values
+
+The values can be found in the reference file `types.user.enum.json`.
diff --git a/types/variant/README.md b/types/variant/README.md
@@ -13,6 +13,8 @@
 4. Empty `std::string`
 5. Empty `std::vector`
 
+The values can be found in the reference file `types.variant.json`.
+
 __Missing:__
 A `std::variant` that is `valueless_by_exception`.
 This requires a type that throws during move assignment.
diff --git a/types/vector/fundamental/README.md b/types/vector/fundamental/README.md
@@ -13,3 +13,5 @@ All child fields use the default column encoding `Int32`.
 2. Empty vectors
 3. Increasing number of elements in the vector:
    one element in the first field, two elements in the second field, etc.
+
+The values can be found in the reference file `types.vector.fundamental.json`.
diff --git a/types/vector/nested/README.md b/types/vector/nested/README.md
@@ -12,3 +12,5 @@ All child fields use the default column encoding `Int32`.
 1. Single-element vectors, with ascending values
 2. Empty vectors
 3. Increasing number of elements in the outer vector, with arbitrary lengths of the inner vectors
+
+The values can be found in the reference file `types.vector.nested.json`.
