From 65d2096fbffec824cc0cb727754e584d6b4ffb7d Mon Sep 17 00:00:00 2001
From: "google-labs-jules[bot]"
 <161369871+google-labs-jules[bot]@users.noreply.github.com>
Date: Sat, 23 May 2026 22:13:00 +0000
Subject: [PATCH] =?UTF-8?q?=E2=9A=A1=20Bolt:=20Optimize=20order-preserving?=
 =?UTF-8?q?=20deduplication=20with=20dict.fromkeys?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Replaced pure-Python `seen` loop mechanisms with the C-optimized `dict.fromkeys()` pattern for order-preserving deduplication of lists and dictionary keys in infrastructure config loaders and batch writer schemas.

Co-authored-by: SatoryKono <13055362+SatoryKono@users.noreply.github.com>
---
 .../application/core/batch_writer_columns_mixin.py    | 11 +++--------
 .../infrastructure/config/base_config_loader.py       |  9 ++-------
 .../infrastructure/config/filter_config_loader.py     | 11 ++---------
 3 files changed, 7 insertions(+), 24 deletions(-)

diff --git a/src/bioetl/application/core/batch_writer_columns_mixin.py b/src/bioetl/application/core/batch_writer_columns_mixin.py
index 718c8b5696..2b663bd586 100644
--- a/src/bioetl/application/core/batch_writer_columns_mixin.py
+++ b/src/bioetl/application/core/batch_writer_columns_mixin.py
@@ -3,6 +3,7 @@
 
 from __future__ import annotations
 
+import itertools
 from typing import TYPE_CHECKING, Literal
 
 if TYPE_CHECKING:
@@ -86,14 +87,8 @@ def _get_schema_columns(
 
     def _collect_record_columns(self, records: list[GoldRecord]) -> list[str]:
         """Collect columns in stable first-seen order."""
-        columns: list[str] = []
-        seen: set[str] = set()
-        for record in records:
-            for key in record:
-                if key not in seen:
-                    seen.add(key)
-                    columns.append(key)
-        return columns
+        # Optimized: C-level iteration and insertion-order preservation via dict.fromkeys
+        return list(dict.fromkeys(itertools.chain.from_iterable(records)))
 
     def _get_column_order(self, columns: Sequence[str]) -> list[str] | None:
         """Resolve explicit column order from configured column groups."""
diff --git a/src/bioetl/infrastructure/config/base_config_loader.py b/src/bioetl/infrastructure/config/base_config_loader.py
index 35b6b8eac0..aed1e5f3c5 100644
--- a/src/bioetl/infrastructure/config/base_config_loader.py
+++ b/src/bioetl/infrastructure/config/base_config_loader.py
@@ -141,13 +141,8 @@ def _merge_lists(
         """
         # Default: simple concatenation with deduplication for string lists
         if base and isinstance(base[0], str):
-            seen: set[str] = set()
-            result: list[str] = []
-            for item in base + override:
-                if item not in seen:
-                    seen.add(item)
-                    result.append(item)
-            return result
+            # Optimized: C-level iteration and insertion-order preservation via dict.fromkeys
+            return list(dict.fromkeys(base + override))
         # Non-string lists: just concatenate
         return base + override
 
diff --git a/src/bioetl/infrastructure/config/filter_config_loader.py b/src/bioetl/infrastructure/config/filter_config_loader.py
index a3e073a641..8d0f601643 100644
--- a/src/bioetl/infrastructure/config/filter_config_loader.py
+++ b/src/bioetl/infrastructure/config/filter_config_loader.py
@@ -304,15 +304,8 @@ def _merge_string_lists(
         Returns:
             Merged list with unique values, base items first.
         """
-        seen: set[str] = set()
-        result: list[str] = []
-
-        for item in base + override:
-            if item not in seen:
-                seen.add(item)
-                result.append(item)
-
-        return result
+        # Optimized: C-level iteration and insertion-order preservation via dict.fromkeys
+        return list(dict.fromkeys(base + override))
 
 
 __all__ = ["FilterConfigLoader"]