fix missing transferto_address in some tron traces

CHANGELOG.md

@@ -3,6 +3,10 @@ All notable changes to this project will be documented in this file.
 
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/).
 
+## [24.07.7/2.3.7] 2024-07-16
+### fixed
+- tron delta-dump: fix missing transferto_address in some tron traces
+
 ## [24.07.6/2.3.6] 2024-07-15
 ### fixed
 - tron delta-dump freezes on grpc asyncio requests

Makefile

@@ -1,8 +1,8 @@
 SHELL := /bin/bash
 PROJECT := graphsense-lib
 VENV := venv
-RELEASE := 'v24.07.6'
-RELEASESEM := 'v2.3.6'
+RELEASE := 'v24.07.7'
+RELEASESEM := 'v2.3.7'
 
 
 all: format lint test build

src/graphsenselib/ingest/transform.py

@@ -106,6 +106,18 @@ def transform(self, block_range_content: BlockRangeContent) -> BlockRangeContent
         traces = drop_columns_from_list(traces, ["block_id_group"])
         logs = drop_columns_from_list(logs, ["block_id_group"])
 
+        def fix_transferToAddress(item):
+            if len(item["transferto_address"]) == 0:
+                # for some very rare txs
+                # e.g. f0b31777dcc58cbca074380ff6f25f8495898edba2da0c43b099b3f276ae3d74
+                # transferTo_address is empty which does not mach our schema.
+                # as a quick fix we set a dummy address for now.
+                dummy_address = b"\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00ikna"  # noqa
+                item["transferto_address"] = dummy_address
+            return item
+
+        traces = [fix_transferToAddress(trace) for trace in traces]
+
         txs = to_bytes(txs, BINARY_COL_CONVERSION_MAP_ACCOUNT_TRX["transaction"])
         blocks = to_bytes(blocks, BINARY_COL_CONVERSION_MAP_ACCOUNT_TRX["block"])
         traces = to_bytes(traces, BINARY_COL_CONVERSION_MAP_ACCOUNT_TRX["trace"])

src/graphsenselib/schema/resources/parquet/account_trx.py

@@ -24,19 +24,6 @@ def set_field_type(schema, field_name, new_type):
 block_schema = set_field_type(block_schema, "gas_used", pa.int64())
 ACCOUNT_TRX_SCHEMA_RAW["block"] = block_schema
 
-# trace_schema = ACCOUNT_TRX_SCHEMA_RAW["trace"]
-# # internal_index', 'transferto_address', 'call_info_index',
-# # 'caller_address', 'call_value', 'rejected', 'call_token_id', 'note
-# trace_schema = set_field_type(trace_schema, "internal_index", pa.int16())
-# trace_schema = set_field_type(trace_schema, "transferto_address", pa.binary(20))
-# trace_schema = set_field_type(trace_schema, "call_info_index", pa.int16())
-# trace_schema = set_field_type(trace_schema, "caller_address", pa.binary(20))
-# trace_schema = set_field_type(trace_schema, "call_value", pa.binary())
-# trace_schema = set_field_type(trace_schema, "rejected", pa.bool_())
-# trace_schema = set_field_type(trace_schema, "call_token_id", pa.int32())
-# trace_schema = set_field_type(trace_schema, "note", pa.string())
-# ACCOUNT_TRX_SCHEMA_RAW["trace"] = trace_schema
-
 transaction_schema = ACCOUNT_TRX_SCHEMA_RAW["transaction"]
 transaction_schema = set_field_type(transaction_schema, "gas", pa.int64())
 ACCOUNT_TRX_SCHEMA_RAW["transaction"] = transaction_schema