From 2a3d3fa0fd04a0434273e2a4f3729fc40758a5cf Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Edgar=20Ram=C3=ADrez=20Mondrag=C3=B3n?=
 <16805946+edgarrmondragon@users.noreply.github.com>
Date: Mon, 26 Aug 2024 17:18:16 -0600
Subject: [PATCH] refactor: Use context manager to read gzip batch files
 (#2628)

* refactor: Use context manager to read gzip batch files

* Remove redundant variable
---
 singer_sdk/sinks/core.py | 20 +++++++++++---------
 1 file changed, 11 insertions(+), 9 deletions(-)

diff --git a/singer_sdk/sinks/core.py b/singer_sdk/sinks/core.py
index 5a936a634..10c278ccb 100644
--- a/singer_sdk/sinks/core.py
+++ b/singer_sdk/sinks/core.py
@@ -611,7 +611,7 @@ def _after_process_record(self, context: dict) -> None:
 
     # SDK developer overrides:
 
-    def preprocess_record(self, record: dict, context: dict) -> dict:  # noqa: ARG002, PLR6301
+    def preprocess_record(self, record: dict, context: dict) -> dict:  # noqa: PLR6301, ARG002
         """Process incoming record and return a modified result.
 
         Args:
@@ -743,12 +743,15 @@ def process_batch_files(
                     tail,
                     mode="rb",
                 ) as file:
-                    context_file = (
-                        gzip_open(file) if encoding.compression == "gzip" else file
-                    )
-                    context = {
-                        "records": [deserialize_json(line) for line in context_file]  # type: ignore[attr-defined]
-                    }
+                    if encoding.compression == "gzip":
+                        with gzip_open(file) as context_file:
+                            context = {
+                                "records": [
+                                    deserialize_json(line) for line in context_file
+                                ]
+                            }
+                    else:
+                        context = {"records": [deserialize_json(line) for line in file]}
                     self.process_batch(context)
             elif (
                 importlib.util.find_spec("pyarrow")
@@ -760,8 +763,7 @@ def process_batch_files(
                     tail,
                     mode="rb",
                 ) as file:
-                    context_file = file
-                    table = pq.read_table(context_file)
+                    table = pq.read_table(file)
                     context = {"records": table.to_pylist()}
                     self.process_batch(context)
             else: