Updated asn1 experiment, now exploring PER and OER

asn1_optimized/GajumaruSerialization.asn

@@ -0,0 +1,235 @@
+-- GajumaruSerialization.asn
+--
+-- ASN.1 model for the structures serialized by gmserialization.erl
+-- (the layer on top of RLP).
+--
+-- Purpose:
+--   * Provide a formal, toolable description of the data.
+--   * Enable migration from the legacy RLP-based format to DER.
+--
+-- Detection of legacy vs new:
+--   Legacy data (produced by gmserialization:serialize / gmser_chain_objects:serialize
+--   or gmser_dyn:serialize) is always an RLP *list* at the top level.
+--   This means the first byte is in the range 0xC0 .. 0xFF.
+--
+--   DER-encoded data using the types below will start with 0x30 (SEQUENCE,
+--   constructed, universal tag) for the outermost GajumaruData (or any
+--   top-level SEQUENCE we define). 0x30 < 0xC0, so a single-byte prefix
+--   check reliably distinguishes the two formats.
+--
+-- Usage in Erlang (after compiling with asn1ct):
+--   {ok, Mod} = asn1ct:compile(GajumaruSerialization.asn, [ber, der]).
+--   {ok, Term} = 'GajumaruSerialization':decode('GajumaruData', DerBinary).
+--
+-- Notes on type mapping from gmserialization.erl:
+--   - int     -> INTEGER          (new data uses canonical DER INTEGER)
+--   - binary  -> OCTET STRING
+--   - bool    -> BOOLEAN
+--   - id      -> Id (SEQUENCE)    (cleaner than the legacy packed 33-byte form)
+--   - [T]     -> SEQUENCE OF T
+--   - {T1,...} -> SEQUENCE        (fixed-size, order matters)
+--   - #{items := [{K,T},...]} -> SEQUENCE with the fields in template order
+--     (static maps carry *values only*, no keys on the wire)
+--   - tag + vsn are preserved as the first two fields for compatibility
+--     with existing dispatch logic.
+--
+--   Legacy integers had strict unsigned-minimal no-leading-zero (except for 0)
+--   and RLP-level rules. New DER data does not need to follow those rules.
+--
+-- WARNING:
+--   Any cryptographic hash or signature computed over a serialized object
+--   will change when switching from RLP to DER for that object. Plan a
+--   coordinated upgrade.
+
+GajumaruSerialization DEFINITIONS
+    AUTOMATIC TAGS ::=
+BEGIN
+
+EXPORTS ALL;
+
+-- ============================================================
+-- Top-level wrapper used for new DER data.
+-- This is what a decoder will see first.
+-- ============================================================
+
+GajumaruData ::= SEQUENCE {
+    -- Constrained for better PER packing
+    tag     INTEGER (0..65535),
+    vsn     INTEGER (0..255),
+    content Content
+}
+
+-- Content can be a specific structured type (preferred) or a generic
+-- representation of a template-driven object.
+Content ::= CHOICE {
+    -- Generic fallback that can represent any [{Field, Type}] template
+    -- without having a pre-defined SEQUENCE for every object.
+    templateFields  [0] TemplateFields,
+
+    -- Static-optimized: no field names on wire (matches legacy static behavior exactly)
+    -- Preferred for compact wire format of known templates.
+    staticFields    [10] StaticFields,
+
+    -- Examples of concrete versioned types (extend as needed)
+    account         [1] Account,
+    signedTx        [2] SignedTx,
+    contract        [3] ContractCode
+    -- Add more alternatives for other tags from gmser_chain_objects
+}
+
+-- ============================================================
+-- Generic template-driven representation
+-- (useful during transition or for unregistered types)
+-- ============================================================
+
+TemplateFields ::= SEQUENCE OF TemplateField
+
+TemplateField ::= SEQUENCE {
+    -- Field name is included for debuggability / generic processing.
+    -- In the original static encoding the name is NOT on the wire;
+    -- only position and type matter. We include it here for convenience.
+    name    IA5String OPTIONAL,
+    value   Value
+}
+
+-- Optimized for static wire format: just the values in order, no names.
+-- This matches the legacy static encoding where maps/records are positional only.
+StaticFields ::= SEQUENCE OF Value
+
+
+Value ::= CHOICE {
+    intValue    [0] INTEGER,
+    boolValue   [1] BOOLEAN,
+    binaryValue [2] OCTET STRING,
+    idValue     [3] Id,
+    listValue   [4] SEQUENCE OF Value,
+    tupleValue  [5] SEQUENCE OF Value,
+    mapValue    [6] SEQUENCE OF KeyValue   -- only needed if you want to
+                                           -- represent dynamic-style maps
+}
+
+KeyValue ::= SEQUENCE {
+    key     Value,
+    val     Value
+}
+
+-- ============================================================
+-- Common types
+-- ============================================================
+
+Id ::= SEQUENCE {
+    -- Corresponds to the simple tags in gmser_id (account=1, name=2, etc.)
+    -- and the extended account subtype (high bit in legacy).
+    type    INTEGER (0..255),
+    value   OCTET STRING (SIZE (32))
+}
+
+-- ============================================================
+-- Concrete object examples (derived from usage in the codebase)
+-- Add / evolve per version as you introduce new vsns.
+-- ============================================================
+
+-- Example: a very simple account-like object used in tests
+Account ::= SEQUENCE {
+    foo     INTEGER,
+    bar     OCTET STRING
+}
+
+-- Simplified signed transaction
+SignedTx ::= SEQUENCE {
+    signatures  SEQUENCE OF OCTET STRING,
+    transaction OCTET STRING
+}
+
+-- Contract code objects (see gmser_contract_code.erl)
+-- We model the three versions that exist today.
+ContractCode ::= CHOICE {
+    v1  [0] ContractV1,
+    v2  [1] ContractV2,
+    v3  [2] ContractV3
+}
+
+ContractV1 ::= SEQUENCE {
+    sourceHash  OCTET STRING,
+    -- typeInfo is a list of 4-tuples in legacy:
+    --   {typeHash, name, argType, outType}
+    typeInfo    SEQUENCE OF TypeInfoV1,
+    byteCode    OCTET STRING
+}
+
+ContractV2 ::= SEQUENCE {
+    sourceHash      OCTET STRING,
+    typeInfo        SEQUENCE OF TypeInfoV1,
+    byteCode        OCTET STRING,
+    compilerVersion OCTET STRING
+}
+
+ContractV3 ::= SEQUENCE {
+    sourceHash      OCTET STRING,
+    typeInfo        SEQUENCE OF TypeInfoV3,
+    byteCode        OCTET STRING,
+    compilerVersion OCTET STRING,
+    payable         BOOLEAN
+}
+
+TypeInfoV1 ::= SEQUENCE {
+    typeHash    OCTET STRING,
+    name        OCTET STRING,
+    argType     OCTET STRING,
+    outType     OCTET STRING
+}
+
+TypeInfoV3 ::= SEQUENCE {
+    typeHash    OCTET STRING,
+    name        OCTET STRING,
+    payable     BOOLEAN,
+    argType     OCTET STRING,
+    outType     OCTET STRING
+}
+
+-- ============================================================
+-- Notes for implementers
+-- ============================================================
+-- 1. Detection (recommended decoder entry point):
+--
+--    decode(Binary) ->
+--        case Binary of
+--            <<B, _/binary>> when B >= 16#C0 ->
+--                decode_legacy_rlp(Binary);   % existing gmser_* path
+--            _ ->
+--                {ok, Term} =
+--                    'GajumaruSerialization':decode('GajumaruData', Binary),
+--                Term
+--        end.
+--
+--    This works because:
+--      - All current top-level output from serialize() is an RLP list
+--        (first byte 0xC0-0xFF).
+--      - GajumaruData and the concrete choices above are SEQUENCEs
+--        (first byte 0x30 for short form, or 0x30 0x81/0x82... for long).
+--
+-- 2. When you add a new object type or version, prefer adding a
+--    concrete SEQUENCE alternative in the Content CHOICE rather than
+--    always falling back to TemplateFields. This gives you better
+--    validation and generated types.
+--
+-- 3. INTEGER in DER is signed and uses a different minimal encoding
+--    than the legacy unsigned big-endian no leading zero form. This is
+--    fine for new data.
+--
+-- 4. If you need to preserve exact legacy integer wire bytes inside
+--    the new format (e.g. for some hash preimage reason), you can
+--    carry selected integers as OCTET STRING (legacy unsigned minimal bytes).
+--
+-- 5. Dynamic encoding (gmser_dyn) is intentionally not modeled here
+--    in full, because it is runtime-schema driven (type codes 246-255,
+--    labels, alt/switch, etc.). You can still use the generic
+--    TemplateFields + Value for some dynamic cases, or model specific
+--    message schemas as additional CHOICE arms.
+--
+-- 6. Compile with DER for canonical output:
+--       asn1ct:compile(GajumaruSerialization, [der]).
+--
+--    The ber option is also accepted; der implies the stricter rules.
+
+END

asn1_optimized/GajumaruSerialization.hrl

@@ -0,0 +1,76 @@
+%% Generated by the Erlang ASN.1 compiler. Version: 5.4.3
+%% Purpose: Erlang record definitions for each named and unnamed
+%% SEQUENCE and SET, and macro definitions for each value
+%% definition in module GajumaruSerialization.
+
+-ifndef(_GAJUMARUSERIALIZATION_HRL_).
+-define(_GAJUMARUSERIALIZATION_HRL_, true).
+
+-record('GajumaruData', {
+  tag,
+  vsn,
+  content
+}).
+
+-record('TemplateField', {
+  name = asn1_NOVALUE,
+  value
+}).
+
+-record('KeyValue', {
+  key,
+  val
+}).
+
+-record('Id', {
+  type,
+  value
+}).
+
+-record('Account', {
+  foo,
+  bar
+}).
+
+-record('SignedTx', {
+  signatures,
+  transaction
+}).
+
+-record('ContractV1', {
+  sourceHash,
+  typeInfo,
+  byteCode
+}).
+
+-record('ContractV2', {
+  sourceHash,
+  typeInfo,
+  byteCode,
+  compilerVersion
+}).
+
+-record('ContractV3', {
+  sourceHash,
+  typeInfo,
+  byteCode,
+  compilerVersion,
+  payable
+}).
+
+-record('TypeInfoV1', {
+  typeHash,
+  name,
+  argType,
+  outType
+}).
+
+-record('TypeInfoV3', {
+  typeHash,
+  name,
+  payable,
+  argType,
+  outType
+}).
+
+-endif. %% _GAJUMARUSERIALIZATION_HRL_