mirror of
https://github.com/Frooodle/Stirling-PDF.git
synced 2026-04-22 23:08:53 +02:00
removal of all getByte loads (#3153)
# Description of Changes Please provide a summary of the changes, including: - What was changed - Why the change was made - Any challenges encountered Closes #(issue_number) --- ## Checklist ### General - [ ] I have read the [Contribution Guidelines](https://github.com/Stirling-Tools/Stirling-PDF/blob/main/CONTRIBUTING.md) - [ ] I have read the [Stirling-PDF Developer Guide](https://github.com/Stirling-Tools/Stirling-PDF/blob/main/DeveloperGuide.md) (if applicable) - [ ] I have read the [How to add new languages to Stirling-PDF](https://github.com/Stirling-Tools/Stirling-PDF/blob/main/HowToAddNewLanguage.md) (if applicable) - [ ] I have performed a self-review of my own code - [ ] My changes generate no new warnings ### Documentation - [ ] I have updated relevant docs on [Stirling-PDF's doc repo](https://github.com/Stirling-Tools/Stirling-Tools.github.io/blob/main/docs/) (if functionality has heavily changed) - [ ] I have read the section [Add New Translation Tags](https://github.com/Stirling-Tools/Stirling-PDF/blob/main/HowToAddNewLanguage.md#add-new-translation-tags) (for new translation tags only) ### UI Changes (if applicable) - [ ] Screenshots or videos demonstrating the UI changes are attached (e.g., as comments or direct attachments in the PR) ### Testing (if applicable) - [ ] I have tested my changes locally. Refer to the [Testing Guide](https://github.com/Stirling-Tools/Stirling-PDF/blob/main/DeveloperGuide.md#6-testing) for more details. --------- Co-authored-by: a <a>
This commit is contained in:
Anthony Stirling
GitHub
@@ -2,122 +2,173 @@
|
||||
|
||||
# Function to check a single webpage
|
||||
check_webpage() {
|
||||
local url=$(echo "$1" | tr -d '\r') # Remove carriage returns
|
||||
local base_url=$(echo "$2" | tr -d '\r')
|
||||
local full_url="${base_url}${url}"
|
||||
local timeout=10
|
||||
echo -n "Testing $full_url ... "
|
||||
|
||||
# Use curl to fetch the page with timeout
|
||||
response=$(curl -s -w "\n%{http_code}" --max-time $timeout "$full_url")
|
||||
if [ $? -ne 0 ]; then
|
||||
echo "FAILED - Connection error or timeout $full_url "
|
||||
return 1
|
||||
fi
|
||||
local url=$(echo "$1" | tr -d '\r') # Remove carriage returns
|
||||
local base_url=$(echo "$2" | tr -d '\r')
|
||||
local full_url="${base_url}${url}"
|
||||
local timeout=10
|
||||
local result_file="$3"
|
||||
|
||||
# Split response into body and status code
|
||||
HTTP_STATUS=$(echo "$response" | tail -n1)
|
||||
BODY=$(echo "$response" | sed '$d')
|
||||
# Use curl to fetch the page with timeout
|
||||
response=$(curl -s -w "\n%{http_code}" --max-time $timeout "$full_url")
|
||||
if [ $? -ne 0 ]; then
|
||||
echo "FAILED - Connection error or timeout $full_url" >> "$result_file"
|
||||
return 1
|
||||
fi
|
||||
|
||||
# Check HTTP status
|
||||
if [ "$HTTP_STATUS" != "200" ]; then
|
||||
echo "FAILED - HTTP Status: $HTTP_STATUS"
|
||||
return 1
|
||||
fi
|
||||
# Split response into body and status code
|
||||
HTTP_STATUS=$(echo "$response" | tail -n1)
|
||||
BODY=$(echo "$response" | sed '$d')
|
||||
|
||||
# Check if response contains HTML
|
||||
if ! printf '%s' "$BODY" | grep -q "<!DOCTYPE html>\|<html"; then
|
||||
echo "FAILED - Response is not HTML"
|
||||
return 1
|
||||
fi
|
||||
# Check HTTP status
|
||||
if [ "$HTTP_STATUS" != "200" ]; then
|
||||
echo "FAILED - HTTP Status: $HTTP_STATUS - $full_url" >> "$result_file"
|
||||
return 1
|
||||
fi
|
||||
|
||||
echo "OK"
|
||||
return 0
|
||||
# Check if response contains HTML
|
||||
if ! printf '%s' "$BODY" | grep -q "<!DOCTYPE html>\|<html"; then
|
||||
echo "FAILED - Response is not HTML - $full_url" >> "$result_file"
|
||||
return 1
|
||||
fi
|
||||
|
||||
echo "OK - $full_url" >> "$result_file"
|
||||
return 0
|
||||
}
|
||||
|
||||
# Main function to test all URLs from the list
|
||||
# Function to test a URL and update counters
|
||||
test_url() {
|
||||
local url="$1"
|
||||
local base_url="$2"
|
||||
local tmp_dir="$3"
|
||||
local url_index="$4"
|
||||
local result_file="${tmp_dir}/result_${url_index}.txt"
|
||||
|
||||
if ! check_webpage "$url" "$base_url" "$result_file"; then
|
||||
echo "1" > "${tmp_dir}/failed_${url_index}"
|
||||
else
|
||||
echo "0" > "${tmp_dir}/failed_${url_index}"
|
||||
fi
|
||||
}
|
||||
|
||||
# Main function to test all URLs from the list in parallel
|
||||
test_all_urls() {
|
||||
local url_file=$1
|
||||
local base_url=${2:-"http://localhost:8080"}
|
||||
local failed_count=0
|
||||
local total_count=0
|
||||
local start_time=$(date +%s)
|
||||
local url_file="$1"
|
||||
local base_url="${2:-"http://localhost:8080"}"
|
||||
local max_parallel="${3:-10}" # Default to 10 parallel processes
|
||||
local failed_count=0
|
||||
local total_count=0
|
||||
local start_time=$(date +%s)
|
||||
local tmp_dir=$(mktemp -d)
|
||||
local active_jobs=0
|
||||
local url_index=0
|
||||
|
||||
echo "Starting webpage tests..."
|
||||
echo "Base URL: $base_url"
|
||||
echo "Number of lines: $(wc -l < "$url_file")"
|
||||
echo "----------------------------------------"
|
||||
|
||||
while IFS= read -r url || [ -n "$url" ]; do
|
||||
# Skip empty lines and comments
|
||||
[[ -z "$url" || "$url" =~ ^#.*$ ]] && continue
|
||||
|
||||
((total_count++))
|
||||
if ! check_webpage "$url" "$base_url"; then
|
||||
((failed_count++))
|
||||
fi
|
||||
done < "$url_file"
|
||||
echo "Starting webpage tests..."
|
||||
echo "Base URL: $base_url"
|
||||
echo "Number of lines: $(wc -l < "$url_file")"
|
||||
echo "Max parallel jobs: $max_parallel"
|
||||
echo "----------------------------------------"
|
||||
|
||||
local end_time=$(date +%s)
|
||||
local duration=$((end_time - start_time))
|
||||
# Process each URL
|
||||
while IFS= read -r url || [ -n "$url" ]; do
|
||||
# Skip empty lines and comments
|
||||
[[ -z "$url" || "$url" =~ ^#.*$ ]] && continue
|
||||
|
||||
((total_count++))
|
||||
((url_index++))
|
||||
|
||||
echo "----------------------------------------"
|
||||
echo "Test Summary:"
|
||||
echo "Total tests: $total_count"
|
||||
echo "Failed tests: $failed_count"
|
||||
echo "Passed tests: $((total_count - failed_count))"
|
||||
echo "Duration: ${duration} seconds"
|
||||
# Run the check in background
|
||||
test_url "$url" "$base_url" "$tmp_dir" "$url_index" &
|
||||
|
||||
# Track the job
|
||||
((active_jobs++))
|
||||
|
||||
# If we've reached max_parallel, wait for a job to finish
|
||||
if [ $active_jobs -ge $max_parallel ]; then
|
||||
wait -n # Wait for any child process to exit
|
||||
((active_jobs--))
|
||||
fi
|
||||
done < "$url_file"
|
||||
|
||||
return $failed_count
|
||||
# Wait for remaining jobs to finish
|
||||
wait
|
||||
|
||||
# Print results in order and count failures
|
||||
for i in $(seq 1 $url_index); do
|
||||
if [ -f "${tmp_dir}/result_${i}.txt" ]; then
|
||||
cat "${tmp_dir}/result_${i}.txt"
|
||||
fi
|
||||
|
||||
if [ -f "${tmp_dir}/failed_${i}" ]; then
|
||||
failed_count=$((failed_count + $(cat "${tmp_dir}/failed_${i}")))
|
||||
fi
|
||||
done
|
||||
|
||||
# Clean up
|
||||
rm -rf "$tmp_dir"
|
||||
|
||||
local end_time=$(date +%s)
|
||||
local duration=$((end_time - start_time))
|
||||
|
||||
echo "----------------------------------------"
|
||||
echo "Test Summary:"
|
||||
echo "Total tests: $total_count"
|
||||
echo "Failed tests: $failed_count"
|
||||
echo "Passed tests: $((total_count - failed_count))"
|
||||
echo "Duration: ${duration} seconds"
|
||||
|
||||
return $failed_count
|
||||
}
|
||||
|
||||
# Print usage information
|
||||
usage() {
|
||||
echo "Usage: $0 [-f url_file] [-b base_url]"
|
||||
echo "Options:"
|
||||
echo " -f url_file Path to file containing URLs to test (required)"
|
||||
echo " -b base_url Base URL to prepend to test URLs (default: http://localhost:8080)"
|
||||
exit 1
|
||||
echo "Usage: $0 [-f url_file] [-b base_url] [-p max_parallel]"
|
||||
echo "Options:"
|
||||
echo " -f url_file Path to file containing URLs to test (required)"
|
||||
echo " -b base_url Base URL to prepend to test URLs (default: http://localhost:8080)"
|
||||
echo " -p max_parallel Maximum number of parallel requests (default: 10)"
|
||||
exit 1
|
||||
}
|
||||
|
||||
# Main execution
|
||||
main() {
|
||||
local url_file=""
|
||||
local base_url="http://localhost:8080"
|
||||
local url_file=""
|
||||
local base_url="http://localhost:8080"
|
||||
local max_parallel=10
|
||||
|
||||
# Parse command line options
|
||||
while getopts ":f:b:h" opt; do
|
||||
case $opt in
|
||||
f) url_file="$OPTARG" ;;
|
||||
b) base_url="$OPTARG" ;;
|
||||
h) usage ;;
|
||||
\?) echo "Invalid option -$OPTARG" >&2; usage ;;
|
||||
esac
|
||||
done
|
||||
# Parse command line options
|
||||
while getopts ":f:b:p:h" opt; do
|
||||
case $opt in
|
||||
f) url_file="$OPTARG" ;;
|
||||
b) base_url="$OPTARG" ;;
|
||||
p) max_parallel="$OPTARG" ;;
|
||||
h) usage ;;
|
||||
\?) echo "Invalid option -$OPTARG" >&2; usage ;;
|
||||
esac
|
||||
done
|
||||
|
||||
# Check if URL file is provided
|
||||
if [ -z "$url_file" ]; then
|
||||
echo "Error: URL file is required"
|
||||
usage
|
||||
fi
|
||||
# Check if URL file is provided
|
||||
if [ -z "$url_file" ]; then
|
||||
echo "Error: URL file is required"
|
||||
usage
|
||||
fi
|
||||
|
||||
# Check if URL file exists
|
||||
if [ ! -f "$url_file" ]; then
|
||||
echo "Error: URL list file not found: $url_file"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
# Run tests using the URL list
|
||||
if test_all_urls "$url_file" "$base_url"; then
|
||||
echo "All webpage tests passed!"
|
||||
exit 0
|
||||
else
|
||||
echo "Some webpage tests failed!"
|
||||
exit 1
|
||||
fi
|
||||
# Check if URL file exists
|
||||
if [ ! -f "$url_file" ]; then
|
||||
echo "Error: URL list file not found: $url_file"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
# Run tests using the URL list
|
||||
if test_all_urls "$url_file" "$base_url" "$max_parallel"; then
|
||||
echo "All webpage tests passed!"
|
||||
exit 0
|
||||
else
|
||||
echo "Some webpage tests failed!"
|
||||
exit 1
|
||||
fi
|
||||
}
|
||||
|
||||
# Run main if script is executed directly
|
||||
if [[ "${BASH_SOURCE[0]}" == "${0}" ]]; then
|
||||
main "$@"
|
||||
main "$@"
|
||||
fi
|
||||
Reference in New Issue
Block a user