Feature/pdf ingestion jpdfium (#6525)

This commit is contained in:
EthanHealy01
2026-06-10 14:51:41 +01:00
committed by GitHub
parent 2aa6768921
commit 5fca2f199a
36 changed files with 2439 additions and 2021 deletions
+1 -2
View File
@@ -233,8 +233,7 @@ Feature: API Validation
When I send the API request to the endpoint "/api/v1/convert/pdf/markdown"
Then the response status code should be 200
And the response file should have size greater than 100
And the response file should have extension ".zip"
And the response ZIP should contain 4 files
And the response file should have extension ".md"
@positive @pdftocsv
+3 -3
View File
@@ -911,7 +911,7 @@ main() {
CUCUMBER_JUNIT_DIR="$PROJECT_ROOT/testing/cucumber/junit"
mkdir -p "$CUCUMBER_JUNIT_DIR"
cd "testing/cucumber"
start_test_timer "Stirling-PDF-Regression"
start_test_timer "Stirling-PDF-Regression $CONTAINER_NAME"
# Snapshot docker log line count before behave so we can extract only behave-window logs
DOCKER_LOG_BEFORE=$(docker logs "$CONTAINER_NAME" 2>&1 | wc -l)
@@ -999,7 +999,7 @@ main() {
# Save docker logs from the behave window to a dedicated file
local cucumber_log="$REPORT_DIR/cucumber-docker-context.log"
docker logs "$CONTAINER_NAME" 2>&1 | tail -n +"$((DOCKER_LOG_BEFORE + 1))" > "$cucumber_log" 2>/dev/null || true
test_failure_logs["Stirling-PDF-Regression"]="$cucumber_log"
test_failure_logs["Stirling-PDF-Regression $CONTAINER_NAME"]="$cucumber_log"
gha_group "Docker logs during behave run: $CONTAINER_NAME"
tail -100 "$cucumber_log"
@@ -1012,7 +1012,7 @@ main() {
capture_file_list "$CONTAINER_NAME" "$AFTER_FILE"
compare_file_lists "$BEFORE_FILE" "$AFTER_FILE" "$DIFF_FILE" "$CONTAINER_NAME"
fi
stop_test_timer "Stirling-PDF-Regression"
stop_test_timer "Stirling-PDF-Regression $CONTAINER_NAME"
fi
# `down` with the override removes the agent bind-mount cleanly. The
# SIGTERM that `down` sends is what triggers dumponexit=true in the