Skip to content

Refine batch failure handling #591

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Draft
dnagoda wants to merge 1 commit into
base: dc.batch-2-preserve-json-order
Choose a base branch
from
Draft

Refine batch failure handling #591

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
34 changes: 25 additions & 9 deletions src/main.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -227,24 +227,25 @@ fn run_batch_mode(
));
};

// Pre-calculate scale factor (constant across all inputs in batch)
// Load schema/query once; scale factor is computed per input.
let schema_string = opts.read_schema_to_string().transpose()?;
let query_string = opts.read_query_to_string().transpose()?;

// Disable profiling in batch mode for performance
let profile_opts = None;

let mut line_num = 0;
let mut processed_count = 0;
let mut success_count = 0;
let mut error_count = 0;
let mut failed_count = 0;

for line_result in input_reader.lines() {
line_num += 1;

let line = match line_result {
Ok(l) => l,
Err(e) => {
error_count += 1;
failed_count += 1;
if opts.batch_continue_on_error {
eprintln!("Error reading line {}: {}", line_num, e);
println!(
Expand All @@ -263,11 +264,13 @@ fn run_batch_mode(
continue;
}

processed_count += 1;

// Parse input
let input = match BytesContainer::new(BytesContainerType::Input, codec, line.into_bytes()) {
Ok(i) => i,
Err(e) => {
error_count += 1;
failed_count += 1;
if opts.batch_continue_on_error {
eprintln!("Error parsing line {}: {}", line_num, e);
println!(r#"{{"success":false,"error":"Invalid JSON input: {}"}}"#, e);
Expand All @@ -292,7 +295,7 @@ fn run_batch_mode(
) {
Ok(sf) => sf,
Err(e) => {
error_count += 1;
failed_count += 1;
if opts.batch_continue_on_error {
eprintln!("Error analyzing schema for line {}: {}", line_num, e);
println!(
Expand Down Expand Up @@ -323,14 +326,27 @@ fn run_batch_mode(
// Output result immediately (streaming JSONL - compact format for line-by-line parsing)
match result {
Ok(function_result) => {
success_count += 1;
let function_succeeded = function_result.success;
if function_succeeded {
success_count += 1;
} else {
failed_count += 1;
}

// Use compact JSON (not pretty-printed) for JSONL format
let compact_json = serde_json::to_string(&function_result)
.unwrap_or_else(|error| error.to_string());
println!("{}", compact_json);

if !function_succeeded && !opts.batch_continue_on_error {
anyhow::bail!(
"Function execution failed on line {}. Review the logs for more information.",
line_num
);
}
}
Err(e) => {
error_count += 1;
failed_count += 1;
if opts.batch_continue_on_error {
eprintln!("Error executing line {}: {}", line_num, e);
println!(r#"{{"success":false,"error":"Execution failed: {}"}}"#, e);
Expand All @@ -343,8 +359,8 @@ fn run_batch_mode(

// Log summary to stderr (so it doesn't interfere with JSONL output on stdout)
eprintln!(
"Batch complete: {} inputs processed, {} successful, {} errors",
line_num, success_count, error_count
"Batch complete: {} inputs processed, {} successful, {} failed",
processed_count, success_count, failed_count
);

Ok(())
Expand Down
70 changes: 70 additions & 0 deletions tests/integration_tests.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -64,6 +64,69 @@ mod tests {
Ok(())
}

#[test]
fn batch_continue_on_error_processes_all_and_counts_function_failures() -> Result<()> {
let mut cmd = Command::new(cargo_bin!());
let input_file = temp_batch_input("{\"code\":0}\n{\"code\":1}\n{\"code\":0}\n")?;

cmd.args(["--function", "tests/fixtures/build/exit_code.wasm"])
.arg("--batch")
.arg("--batch-continue-on-error")
.arg("--input")
.arg(input_file.as_os_str());

let output = cmd.output()?;

assert!(output.status.success());

let stdout = String::from_utf8(output.stdout)?;
let results = stdout
.lines()
.map(serde_json::from_str::<serde_json::Value>)
.collect::<Result<Vec<_>, _>>()?;
assert_eq!(results.len(), 3);
assert_eq!(results[0]["success"], true);
assert_eq!(results[1]["success"], false);
assert_eq!(results[2]["success"], true);

assert_eq!(
String::from_utf8(output.stderr)?,
"Batch complete: 3 inputs processed, 2 successful, 1 failed\n"
);

Ok(())
}

#[test]
fn batch_stops_on_function_failure_by_default() -> Result<()> {
let mut cmd = Command::new(cargo_bin!());
let input_file = temp_batch_input("{\"code\":0}\n{\"code\":1}\n{\"code\":0}\n")?;

cmd.args(["--function", "tests/fixtures/build/exit_code.wasm"])
.arg("--batch")
.arg("--input")
.arg(input_file.as_os_str());

let output = cmd.output()?;

assert!(!output.status.success());

let stdout = String::from_utf8(output.stdout)?;
let results = stdout
.lines()
.map(serde_json::from_str::<serde_json::Value>)
.collect::<Result<Vec<_>, _>>()?;
assert_eq!(results.len(), 2);
assert_eq!(results[0]["success"], true);
assert_eq!(results[1]["success"], false);

assert!(String::from_utf8(output.stderr)?.contains(
"Function execution failed on line 2. Review the logs for more information."
));

Ok(())
}

#[test]
fn run_no_opts() -> Result<()> {
let mut cmd = Command::new(cargo_bin!());
Expand Down Expand Up @@ -265,6 +328,13 @@ mod tests {
Ok(file)
}

fn temp_batch_input(jsonl: &str) -> Result<assert_fs::NamedTempFile> {
let file = assert_fs::NamedTempFile::new("input.jsonl")?;
file.write_str(jsonl)?;

Ok(file)
}

#[test]
fn test_scale_limits_analyzer_use_defaults_when_query_and_schema_not_provided() -> Result<()> {
let mut cmd = Command::new(cargo_bin!());
Expand Down
Loading