fix cluster mapping on invalid addresses

CHANGELOG.md

@@ -1,5 +1,9 @@
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/).
 
+## [24.01.7] 2024-07-19
+### fixed
+- fix cluster mapping errors on invalid addresses. Instead just skip them.
+
 ## [24.01.6] 2024-06-20
 ### fixed
 - avoid errors with numpy 2.0 setting version restriction to < 2.0

Makefile

@@ -1,7 +1,7 @@
 SHELL := /bin/bash
 PROJECT := tagpack-tool
 VENV := .venv
-RELEASE := 'v24.01.6'
+RELEASE := 'v24.01.7'
 # RELEASESEM := 'v1.9.0'
 
 all: format lint test build

src/tagpack/actorpack.py

@@ -1,4 +1,5 @@
 """ActorPack - A wrapper for ActorPack files"""
+
 import json
 import os
 import re

src/tagpack/actorpack_schema.py

@@ -1,4 +1,5 @@
 """ActorPack - A wrappers ActorPack Schema"""
+
 import importlib.resources as pkg_resources
 
 import pandas as pd

src/tagpack/cmd_utils.py

@@ -1,4 +1,5 @@
 """Utilities for a more beautiful CMD interface"""
+
 import os
 
 

src/tagpack/graphsense.py

@@ -211,6 +211,10 @@ def get_address_ids(self, df: DataFrame, currency: str) -> DataFrame:
                 lambda x: eth_address_from_hex(x)
             )
 
+            # the last step can fail two, eg, wrongly encoded addresses
+            # so we filter again filter non convertible addresses
+            df_temp = df_temp[df_temp["address"].notnull()]
+
         elif currency == "ETH":
             df_temp["address_prefix"] = df_temp["address"].str[
                 2 : 2 + ks_config["address_prefix_length"]
@@ -220,6 +224,10 @@ def get_address_ids(self, df: DataFrame, currency: str) -> DataFrame:
             )
 
             df_temp["address"] = df["address"].apply(lambda x: eth_address_from_hex(x))
+
+            # the last step can fail two, eg, wrongly encoded addresses
+            # so we filter again filter non convertible addresses
+            df_temp = df_temp[df_temp["address"].notnull()]
         else:
             if "bech_32_prefix" in ks_config:
                 df_temp["a"] = df_temp["address"].apply(

src/tagpack/tagpack.py

@@ -1,4 +1,5 @@
 """TagPack - A wrapper for TagPacks files"""
+
 import glob
 import hashlib
 import json
@@ -271,9 +272,11 @@ def get_unique_tags(self):
             # check if duplicate entry
             t = tuple(
                 [
-                    str(tag.all_fields.get(k)).lower()
-                    if k in tag.all_fields.keys()
-                    else ""
+                    (
+                        str(tag.all_fields.get(k)).lower()
+                        if k in tag.all_fields.keys()
+                        else ""
+                    )
                     for k in ["address", "currency", "label", "source"]
                 ]
             )

src/tagpack/tagpack_schema.py

@@ -1,4 +1,5 @@
 """TagPack - A wrappers TagPack Schema"""
+
 import importlib.resources as pkg_resources
 
 import pandas as pd