From 8e0635b8ba1e5499c8d3b502803a4d35fce5de26 Mon Sep 17 00:00:00 2001
From: chrislu <chris.lu@gmail.com>
Date: Sun, 23 Nov 2025 20:32:57 -0800
Subject: [PATCH] fix: search for filename in 'Encountered error' message

The issue: grep pattern was wrong and looking in wrong place
- EOF exception is in the 'Caused by' section
- Filename is in the outer exception message

The fix:
- Search for 'Encountered error while reading file' line
- Extract filename: part-00000-xxx-c000.snappy.parquet
- Fixed regex pattern (was missing dash before c000)

Example from logs:
  'Encountered error while reading file seaweedfs://...part-00000-c5a41896-5221-4d43-a098-d0839f5745f6-c000.snappy.parquet'

This will finally extract the right filename!
---
 .github/workflows/spark-integration-tests.yml | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/.github/workflows/spark-integration-tests.yml b/.github/workflows/spark-integration-tests.yml
index ebd43e1dc..3bf1c6550 100644
--- a/.github/workflows/spark-integration-tests.yml
+++ b/.github/workflows/spark-integration-tests.yml
@@ -138,11 +138,15 @@ jobs:
               # Get the full log and extract the EXACT file causing the error
               FULL_LOG=$(docker compose logs spark-tests 2>&1)
               
-              # Extract the failing filename from the EOF error message
-              # The error message format: "...seaweedfs://seaweedfs-filer:8888/test-spark/employees/part-xxx.parquet..."
-              FAILING_FILE=$(echo "$FULL_LOG" | grep -B 5 "EOFException.*78 bytes" | grep "seaweedfs://" | grep -oP 'part-[a-f0-9-]+\.c000\.snappy\.parquet' | head -1)
+              # Extract the failing filename from the error message
+              # Look for "Encountered error while reading file seaweedfs://...part-xxx-c000.snappy.parquet"
+              FAILING_FILE=$(echo "$FULL_LOG" | grep "Encountered error while reading file" | grep -oP 'part-[a-f0-9-]+-c000\.snappy\.parquet' | head -1)
               echo "Failing file: $FAILING_FILE"
               
+              # Also show the full error line for debugging
+              echo "Full error context:"
+              echo "$FULL_LOG" | grep "Encountered error while reading file" | head -1
+              
               if [ -z "$FAILING_FILE" ]; then
                 echo "ERROR: Could not extract failing filename from error message"
                 echo "Searching for error message pattern..."