From 24f0939c62a0c07b6953aec78cdf2821ca4538a4 Mon Sep 17 00:00:00 2001
From: Sean Kelly <10122262+skellys@users.noreply.github.com>
Date: Mon, 30 Oct 2023 14:09:51 -0400
Subject: [PATCH] fix: partition evaluator thread safety

---
 pyiceberg/table/__init__.py | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/pyiceberg/table/__init__.py b/pyiceberg/table/__init__.py
index ae35b34384..21a3b7fc23 100644
--- a/pyiceberg/table/__init__.py
+++ b/pyiceberg/table/__init__.py
@@ -828,8 +828,12 @@ def _build_partition_evaluator(self, spec_id: int) -> Callable[[DataFile], bool]
         partition_schema = Schema(*partition_type.fields)
         partition_expr = self.partition_filters[spec_id]
 
-        evaluator = visitors.expression_evaluator(partition_schema, partition_expr, self.case_sensitive)
-        return lambda data_file: evaluator(data_file.partition)
+        # The lambda created here is run in multiple threads.
+        # So we avoid creating _EvaluatorExpression methods bound to a single
+        # shared instance across multiple threads.
+        return lambda data_file: visitors.expression_evaluator(partition_schema, partition_expr, self.case_sensitive)(
+            data_file.partition
+        )
 
     def _check_sequence_number(self, min_data_sequence_number: int, manifest: ManifestFile) -> bool:
         """Ensure that no manifests are loaded that contain deletes that are older than the data.