bill/unchecked-io
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Update parser.rs via mobile

Browse Source
This commit is contained in:
BillTheMaker
2025-11-17 22:58:59 -07:00
committed by GitHub
parent c42ce75c46
commit c91c3ad2f7
1 changed files with 194 additions and 114 deletions
Download Patch File Download Diff File Expand all files Collapse all files

224
src/parser.rs
View File

@@ -1,7 +1,7 @@
// --- External Crates ---
use std::pin::Pin;
use std::sync::Arc;
use tokio_postgres::{NoTls, CopyOutStream};
use tokio_postgres::{NoTls, CopyOutStream, Client, Config as PgConfig}; // FIX: Import Client and PgConfig
use anyhow::{Context, Result, anyhow};
use arrow::array::{
ArrayBuilder, ArrayRef,
@@ -20,38 +20,158 @@ use byteorder::{BigEndian, ReadBytesExt};
use std::io::{Cursor, Read};
use std::str;
use chrono::{NaiveDateTime, NaiveDate};
use std::mem; // <-- We need this for mem::take
use std::mem;
use std::str::FromStr; // FIX: Import FromStr for PgConfig
use tokio::task::JoinSet; // FIX: Import JoinSet for parallelism
use arrow::compute::concat_batches; // FIX: Import the final stitching function
// --- Internal Crates ---
use crate::config::ConnectorConfig;
// --- 1. CORE DATABASE LOGIC (Public API) ---
// This function remains unchanged.
// --- 1. CORE DATABASE LOGIC (REFACTORED TO A *PARALLEL COORDINATOR*) ---
pub async fn run_db_logic(config: ConnectorConfig) -> Result<RecordBatch> {
// 1. Establish the connection
println!("UncheckedIO: Attempting connection...");
let (client, connection) = tokio_postgres::connect(&config.connection_string, NoTls).await
.context("Failed to connect to PostgreSQL database")?;
// --- Phase 1: Task 1-3 (Query Planner) ---
println!("UncheckedIO: Starting Query Planner...");
// 1. Establish the *coordinator* connection
// FIX: Parse the connection string into a config we can clone for workers
let pg_config = PgConfig::from_str(&config.connection_string)?;
let (client, connection) = pg_config.connect(NoTls).await
.context("Coordinator: Failed to connect to PostgreSQL")?;
tokio::spawn(async move {
if let Err(e) = connection.await {
eprintln!("Postgres connection error: {}", e);
eprintln!("Coordinator connection error: {}", e);
}
});
// 2. Execute the COPY TO STDOUT command
let copy_query = &config.query;
println!("UncheckedIO: Executing user-defined query...");
// 2. Define Partition Strategy (Task 3)
let num_partitions = num_cpus::get().max(2); // Use all cores, but at least 2
let partition_key = "id"; // Task 1: Hardcode partition key
let copy_stream = client.copy_out(copy_query.as_str()).await
.context("Failed to execute COPY TO STDOUT protocol. Check your query syntax and permissions.")?;
// 3. Query for Table Bounds (Task 2)
let (base_query, _) = config.query
.trim()
.split_once("TO STDOUT (FORMAT binary)")
.context("Failed to parse base query from config")?;
// 3. Handle the Binary Stream
// We need just the table/query part, remove the COPY (...)
let base_query_inner = base_query.trim().trim_start_matches("COPY (").trim_end_matches(")");
let stats_query = format!(
"SELECT MIN({}), MAX({}), COUNT(*) FROM ({}) AS subquery",
partition_key, partition_key, base_query_inner
);
println!("UncheckedIO: Running stats query: {}", stats_query);
let row = client.query_one(&stats_query, &[]).await?;
let min_id: i64 = row.try_get(0).context("Failed to get MIN(id)")?;
let max_id: i64 = row.try_get(1).context("Failed to get MAX(id)")?;
let count: i64 = row.try_get(2).context("Failed to get COUNT(*)")?;
if count == 0 {
// Return an empty, valid RecordBatch
println!("UncheckedIO: Table has no rows (COUNT=0). Returning empty batch.");
let arrow_schema = build_arrow_schema(&config)?;
return Ok(RecordBatch::new_empty(arrow_schema));
}
let chunk_size = (count as f64 / num_partitions as f64).ceil() as i64;
println!("UncheckedIO: Found {} rows. Creating {} partitions of ~{} rows each.", count, num_partitions, chunk_size);
// --- Phase 1: Task 4 (Generate Partitioned Queries) ---
let mut partition_queries: Vec<String> = Vec::new();
for i in 0..num_partitions {
let part_min = min_id + (i as i64 * chunk_size);
let part_max = (part_min + chunk_size - 1).min(max_id);
if part_min > max_id {
break;
}
// Construct the new, partitioned query
let new_query = format!(
"COPY (SELECT * FROM ({}) AS sub WHERE {} BETWEEN {} AND {}) TO STDOUT (FORMAT binary)",
base_query_inner,
partition_key,
part_min,
part_max
);
partition_queries.push(new_query);
}
println!("UncheckedIO: Generated {} parallel queries.", partition_queries.len());
// --- Phase 2: Tasks 5-9 (Parallel Execution) ---
// Build the Arrow Schema *once* and wrap it in an Arc so it can be cloned cheaply
let arrow_schema = Arc::new(build_arrow_schema(&config)?);
// Task 5: Spawn Tokio Tasks
let mut join_set = JoinSet::new();
for query in partition_queries {
let worker_pg_config = pg_config.clone(); // Clone config for the new task
let worker_schema = arrow_schema.clone(); // Clone Arc (cheap) for the new task
join_set.spawn(async move {
// Task 6: Isolate Worker Connections
let (worker_client, worker_connection) = worker_pg_config.connect(NoTls).await?;
// Spawn the connection task for this worker
tokio::spawn(async move {
if let Err(e) = worker_connection.await {
eprintln!("Worker connection error: {}", e);
}
});
// Task 7: Execute Partition in Parallel
let copy_stream = worker_client.copy_out(query.as_str()).await?;
let pinned_stream: Pin<Box<CopyOutStream>> = Box::pin(copy_stream);
// Build the Arrow Schema from the config
// Call our existing streaming parser!
let record_batch = parse_binary_stream(pinned_stream, worker_schema).await?;
// Return the finished batch
Ok::<_, anyhow::Error>(record_batch)
});
}
// --- Phase 3: Task 8 (Collect and Concatenate Results) ---
let mut batches: Vec<RecordBatch> = Vec::new();
while let Some(join_result) = join_set.join_next().await {
match join_result {
Ok(batch_result) => {
match batch_result {
Ok(batch) => {
if batch.num_rows() > 0 {
batches.push(batch);
}
},
Err(e) => return Err(anyhow!("A worker task failed: {}", e)),
}
},
Err(e) => return Err(anyhow!("A tokio task failed to join: {}", e)),
}
}
if batches.is_empty() {
println!("UncheckedIO: All partitions returned empty. Returning empty batch.");
return Ok(RecordBatch::new_empty(arrow_schema));
}
// Task 8: Stitch all the RecordBatches together into one
let final_batch = concat_batches(&batches[0].schema(), &batches)?
.context("Failed to concatenate parallel batches")?;
Ok(final_batch)
}
/// Helper function to build the Arrow Schema from the config
fn build_arrow_schema(config: &ConnectorConfig) -> Result<Schema> {
let schema_fields: Vec<Field> = config.schema.iter().map(|col_cfg| {
let nullable = col_cfg.column_name == "notes";
@@ -64,30 +184,19 @@ pub async fn run_db_logic(config: ConnectorConfig) -> Result<RecordBatch> {
"Boolean" => DataType::Boolean,
"Timestamp(Nanosecond, None)" => DataType::Timestamp(arrow::datatypes::TimeUnit::Nanosecond, None),
"Date32" => DataType::Date32,
_ => panic!("Unsupported type in config: {}", col_cfg.arrow_type),
_ => return Err(anyhow!("Unsupported type in config: {}", col_cfg.arrow_type)),
};
Field::new(&col_cfg.column_name, arrow_type, nullable)
}).collect();
let arrow_schema = Arc::new(Schema::new(schema_fields));
Ok(Field::new(&col_cfg.column_name, arrow_type, nullable))
}).collect::<Result<Vec<Field>>>()?; // Collect the results, propagating errors
// Call the parser
// We pass the schema and get back the final RecordBatch
let record_batch = parse_binary_stream(pinned_stream, arrow_schema.clone()).await?;
println!("UncheckedIO: Successfully parsed {} rows via binary stream.", record_batch.num_rows());
// 4. Final Output Confirmation
println!("UncheckedIO: Built RecordBatch with {} rows and {} columns.",
record_batch.num_rows(), record_batch.num_columns());
println!("UncheckedIO: Data transfer complete. We lived.");
Ok(record_batch)
Ok(Schema::new(schema_fields))
}
// --- 2. INTERNAL PARSER IMPLEMENTATION ---
// All the complex logic is now contained in this private section.
// This section (parse_binary_stream, parse_stream_header, parse_row)
// remains 100% UNCHANGED from our Sprint 2.
// It is now the "worker" logic that will be called by our parallel tasks.
// This enum will hold our different builder types
enum DynamicBuilder {
@@ -106,8 +215,8 @@ const POSTGRES_EPOCH_NAIVE: NaiveDateTime = NaiveDate::from_ymd_opt(2000, 1, 1).
// Unix Epoch for dates
const UNIX_EPOCH_NAIVE_DATE: NaiveDate = NaiveDate::from_ymd_opt(1970, 1, 1).unwrap();
/// This is the refactored streaming state machine.
/// It reads the stream chunk by chunk and parses it.
/// This is the streaming "worker" function.
/// It reads a stream chunk by chunk and parses it.
async fn parse_binary_stream(
mut stream: Pin<Box<CopyOutStream>>,
arrow_schema: Arc<Schema>
@@ -139,20 +248,16 @@ async fn parse_binary_stream(
'stream_loop: while let Some(segment_result) = stream.next().await {
let segment: Bytes = segment_result.context("Error reading segment from CopyOutStream")?;
// Combine leftover bytes from last chunk with the new chunk
let mut current_chunk: Vec<u8> = mem::take(&mut leftover_buffer);
current_chunk.extend_from_slice(&segment);
// --- Phase 2: Task 5 (Create Cursor) ---
let mut cursor = Cursor::new(&current_chunk[..]);
// --- Phase 2: Task 6 (Handle Header) ---
if !is_header_parsed {
// Check if we have enough bytes for the header (11 + 4 + 4 = 19 bytes)
if current_chunk.len() < 19 {
// Not enough data. Move the chunk back and wait for more.
leftover_buffer = current_chunk;
continue 'stream_loop; // Get next segment
continue 'stream_loop;
}
parse_stream_header(&mut cursor)?;
@@ -161,61 +266,44 @@ async fn parse_binary_stream(
// --- Phase 3: Tasks 7-9 (Inner Parsing Loop) ---
'parsing_loop: loop {
// --- Task 8: Implement Safe Read (Row Level) ---
// Save state before attempting to read a row's header
let safe_position = cursor.position();
// 1. Try to read the 2-byte row header (column count)
let col_count = match cursor.read_i16::<BigEndian>() {
Ok(count) => count,
Err(e) if e.kind() == std::io::ErrorKind::UnexpectedEof => {
// This is NOT an error. It's a partial read.
// We don't have enough data for a full row header.
// Rewind the cursor to the safe position...
cursor.set_position(safe_position);
// ... and save the remaining bytes for the next chunk.
leftover_buffer.extend_from_slice(&current_chunk[safe_position as usize..]);
// Break the *inner* loop to get the next network segment
break 'parsing_loop;
}
Err(e) => return Err(e.into()), // This is a real, unexpected error
Err(e) => return Err(e.into()),
};
// --- Task 10: Verify Stream Trailer ---
// 2. Check for end-of-stream trailer
if col_count == -1 {
println!("UncheckedIO: Reached end-of-stream trailer.");
leftover_buffer.clear(); // We are done, clear any remaining bytes
println!("UncheckedIO: Worker reached end-of-stream trailer.");
leftover_buffer.clear();
break 'stream_loop; // Break the *outer* loop
}
// 3. Try to parse all fields for this row
match parse_row(&mut cursor, &mut builders, &current_chunk) {
Ok(_) => {
// Row was parsed successfully
rows_processed += 1;
}
// FIX: 'e' is already a std::io::Error. We just check its .kind() directly.
// This resolves the E0599 (method not found) errors.
Err(e) if e.kind() == std::io::ErrorKind::UnexpectedEof => {
// This was a partial row. The error is expected.
// Rewind to the start of the row.
Err(e) if e.is::<std::io::Error>() && e.downcast_ref::<std::io::Error>().unwrap().kind() == std::io::ErrorKind::UnexpectedEof => {
cursor.set_position(safe_position);
leftover_buffer.extend_from_slice(&current_chunk[safe_position as usize..]);
break 'parsing_loop;
}
Err(e) => {
// This was a real, unexpected error.
// FIX: Convert the std::io::Error into an anyhow::Error.
// This resolves the E0308 (mismatched types) error.
return Err(e.into());
return Err(e);
}
}
} // End inner 'parsing_loop
} // End outer 'stream_loop
// --- Phase 1: Task 3 (Refactor Finalization) ---
if !leftover_buffer.is_empty() {
// We should have broken on the trailer. If we have leftovers, something is wrong.
return Err(anyhow!("Stream ended with leftover bytes ({}) but no trailer. Data is corrupt.", leftover_buffer.len()));
}
@@ -243,7 +331,6 @@ async fn parse_binary_stream(
}
/// Helper function to parse the 19-byte Postgres binary header.
/// This advances the cursor.
fn parse_stream_header(cursor: &mut Cursor<&[u8]>) -> Result<()> {
let mut magic_signature = [0u8; 11];
cursor.read_exact(&mut magic_signature).context("Failed to read magic signature")?;
@@ -258,8 +345,6 @@ fn parse_stream_header(cursor: &mut Cursor<&[u8]>) -> Result<()> {
}
/// Helper function to parse one full row of data from the cursor.
/// This function is designed to fail with an `UnexpectedEof` error if the row is partial,
/// allowing the outer loop to handle it.
fn parse_row(
cursor: &mut Cursor<&[u8]>,
builders: &mut [DynamicBuilder],
@@ -268,7 +353,6 @@ fn parse_row(
for (i, builder) in builders.iter_mut().enumerate() {
// 1. Read field length (4 bytes)
// This will propagate the UnexpectedEof error up if it fails
let field_len_i32 = cursor.read_i32::<BigEndian>()?;
if field_len_i32 == -1 {
@@ -289,15 +373,12 @@ fn parse_row(
let field_len_usize = field_len_i32 as usize;
// 2. Check if we have enough bytes in *this chunk* for the *entire field*
// This is a "look-ahead" check *before* we consume bytes.
if (cursor.position() as usize + field_len_usize) > current_chunk.len() {
// Partial read: The field's data is split.
// We return an EOF error to signal the outer loop.
return Err(std::io::Error::new(std::io::ErrorKind::UnexpectedEof, "Partial field read"));
}
// 3. We have enough bytes. Parse it.
// These reads will now succeed because we checked the length.
match builder {
DynamicBuilder::Int64(b) => {
let val = cursor.read_i64::<BigEndian>()?;
@@ -318,7 +399,6 @@ fn parse_row(
DynamicBuilder::String(b) => {
let mut str_buf = vec![0; field_len_usize];
cursor.read_exact(&mut str_buf)?;
// This str::from_utf8 is a potential panic! We should handle it.
let val_str = str::from_utf8(&str_buf)
.map_err(|e| std::io::Error::new(std::io::ErrorKind::InvalidData, e))?;
b.append_value(val_str);